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. 4-GEMMASCOPE-RES-16K
    6. 3358
    Prev
    Next
    INDEX
    Explanations

    statements or questions concerning the topic at hand

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ')")
    -0.69
     manières
    -0.68
    featureID
    -0.66
    RectangleBorder
    -0.65
    ">',
    -0.65
     Psyche
    -0.65
     ProductService
    -0.64
    '>";
    -0.62
    Πηγές
    -0.61
    FieldBuilder
    -0.61
    POSITIVE LOGITS
     maybe
    0.54
     الحره
    0.53
    次は
    0.53
    жели
    0.51
    StartsWith
    0.50
    比如
    0.50
    前は
    0.49
    なら
    0.48
    不如
    0.48
    ̣ng
    0.48
    Activations Density 0.174%

    No Known Activations