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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 1505
    Prev
    Next
    INDEX
    Explanations

    lists and collections of items or elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code that uses append/push functions

    np_acts-logits-general · gemini-2.0-flash

    append or push to a list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.61
    !("{}",
    -0.50
     szól
    -0.50
    EndContext
    -0.48
    onViewCreated
    -0.48
     blessés
    -0.48
    straint
    -0.47
    subtract
    -0.46
    ctica
    -0.46
     avanzado
    -0.45
    POSITIVE LOGITS
     push
    1.04
    push
    1.02
     pushed
    0.84
     Push
    0.83
     pushes
    0.83
     PUSH
    0.83
     pushing
    0.78
     Pushing
    0.74
    PUSH
    0.72
     pusher
    0.70
    Activations Density 0.133%

    No Known Activations