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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 9329
    Prev
    Next
    INDEX
    Explanations

    instances of emphasis and negation in statements

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

    Token surrounded by punctuation

    np_acts-logits-general · gemini-2.0-flash

    word sequences after specific tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    1
    -0.29
     the
    -0.28
     of
    -0.26
        
    -0.25
     -
    -0.25
     upon
    -0.24
     '
    -0.24
     with
    -0.24
     for
    -0.23
     sus
    -0.23
    POSITIVE LOGITS
    niſſe
    0.98
     propOrder
    0.96
    ſelben
    0.96
     ویکی‌پدی
    0.96
    iſchen
    0.95
    ésultats
    0.94
    iſen
    0.92
     queſta
    0.91
    [@BOS@]
    0.90
    <unused28>
    0.89
    Activations Density 0.382%

    No Known Activations