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. 20-GEMMASCOPE-RES-16K
    6. 9818
    Prev
    Next
    INDEX
    Explanations

    code-related syntax elements and structures such as functions, conditionals, and cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     ujednoznacz
    -0.86
    NgModule
    -0.72
     estimés
    -0.71
    addPreferredGap
    -0.61
     cref
    -0.60
    jspb
    -0.56
     NgModule
    -0.55
     Humberto
    -0.55
    also
    -0.55
     שוליים
    -0.54
    POSITIVE LOGITS
    Попис
    0.62
    DIPSETTING
    0.57
     الرياضيه
    0.55
    String
    0.55
     فريبيس
    0.53
     String
    0.52
    LLocation
    0.52
     Ause
    0.50
     ddelweddau
    0.49
    tivitas
    0.48
    Activations Density 0.026%

    No Known Activations