© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12568
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical analysis results

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

    Section or subsection numbering

    np_acts-logits-general · gemini-2.0-flash

    section numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     queſta
    -0.64
     Geſch
    -0.64
     незавершена
    -0.62
    OGND
    -0.62
     geſch
    -0.60
    ſchaft
    -0.60
    ьажоргаш
    -0.59
     zwiſchen
    -0.58
    niſſe
    -0.58
     geſ
    -0.58
    POSITIVE LOGITS
    <h2>
    0.37
    ieteur
    0.34
    F
    0.32
    '
    0.31
    subsubsection
    0.30
    льзя
    0.30
     CURLOPT
    0.29
    <h4>
    0.28
    <h3>
    0.28
     plutôt
    0.28
    Activations Density 0.236%

    No Known Activations