© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 8451
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to numerical methods and estimators in mathematical modeling

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

    descriptions of proposed or developed methods in academic or technical papers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SizeMode
    -0.33
    шку
    -0.29
     figura
    -0.29
     литров
    -0.29
     Tentang
    -0.29
    usters
    -0.28
     points
    -0.28
    shaped
    -0.28
    chauffer
    -0.28
     allzu
    -0.27
    POSITIVE LOGITS
    enterOuterAlt
    0.84
     հղումներ
    0.75
     technique
    0.69
     techniques
    0.67
     methodology
    0.66
     Technique
    0.65
    SourceChecksum
    0.64
     Techniques
    0.63
     method
    0.63
    цездатний
    0.63
    Activations Density 1.818%

    No Known Activations