© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 3916
    Prev
    Next
    INDEX
    Explanations

    instances of dashes or em dashes used for emphasis or as separators in text

    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
    
    -0.98
     ´
    -0.95
    <?=
    -0.93
     <?=
    -0.88
    Eqn
    -0.84
     
    -0.83
    
    -0.81
     
    -0.81
    {`
    -0.81
     Vikipedi
    -0.80
    POSITIVE LOGITS
     —
    2.27
    —
    1.69
    ——
    1.62
    ———
    1.54
     —,
    1.45
    )—
    1.41
    —————
    1.39
    .—
    1.36
    —-
    1.36
    "—
    1.36
    Activations Density 0.360%

    No Known Activations