© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 769
    Prev
    Next
    INDEX
    Explanations

    concepts related to algorithms and their performance in probabilistic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical and algorithmic terminology, especially related to probability, computational complexity, and technical papers.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    technical theoretical-computer-science content about algorithmic tractability and circuit/graph structure (e.g., discussions of algorithms, treewidth, and Boolean circuits)

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    technical or mathematical text discussing algorithms, computational complexity, and formal proofs.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ImageField
    -0.42
     Secretario
    -0.36
     الحره
    -0.34
    ticias
    -0.32
     actrice
    -0.32
    octave
    -0.31
    Wallis
    -0.31
     retires
    -0.31
     secretario
    -0.30
    Rhestr
    -0.29
    POSITIVE LOGITS
    :✨
    0.75
    tanleria
    0.59
     transfieras
    0.50
    scriptcase
    0.50
     CanadaChoose
    0.50
     preocupes
    0.50
     ffilmiau
    0.49
     lenker
    0.49
    kloped
    0.49
     चीज़ों
    0.48
    Activations Density 1.288%

    No Known Activations