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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12190
    Prev
    Next
    INDEX
    Explanations

    references to lifestyle transformations or choices

    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
    il
    -0.67
    the
    -0.66
    al
    -0.65
    ub
    -0.65
    ou
    -0.62
    3
    -0.61
    <strong>
    -0.58
    ãng
    -0.58
    ul
    -0.57
    ut
    -0.57
    POSITIVE LOGITS
    capable
    1.25
     capable
    1.16
    |}{$
    1.04
     incapable
    0.99
    >\<^
    0.98
    djangoproject
    0.91
     disappear
    0.90
    Grüße
    0.90
    hematical
    0.89
    adecimal
    0.88
    Activations Density 0.062%

    No Known Activations