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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 6425
    Prev
    Next
    INDEX
    Explanations

    code blocks and structures with defined access modifiers and parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ProtoMessage
    -0.77
     فريبيس
    -0.76
    WriteTagHelper
    -0.70
    aarrggbb
    -0.66
    saraba
    -0.65
     doch
    -0.63
    featureID
    -0.63
    ISupport
    -0.62
     ویکی‌پدی
    -0.61
    AnchorStyles
    -0.61
    POSITIVE LOGITS
    )».
    0.61
    public
    0.48
    حياته
    0.48
     impossibile
    0.47
     */;
    0.47
    iParam
    0.46
    private
    0.46
    டம்
    0.45
    };*/
    0.45
     Audiodateien
    0.45
    Activations Density 0.279%

    No Known Activations