Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 4717
    Prev
    Next
    INDEX
    Explanations

    phrases that quantify a particular "amount" of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flare
    -0.78
     flares
    -0.72
     '/';
    -0.72
    cookieParser
    -0.72
     Flare
    -0.70
     ['./
    -0.70
     Vle
    -0.68
    ickson
    -0.68
    gotoxy
    -0.68
     NDEBUG
    -0.68
    POSITIVE LOGITS
     amount
    1.99
     amounts
    1.85
     Amount
    1.75
     AMOUNT
    1.70
     Amounts
    1.70
    amount
    1.67
    Amount
    1.59
    amounts
    1.56
    Amounts
    1.54
    getAmount
    1.52
    Activations Density 0.107%

    No Known Activations