© 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. 4-GEMMASCOPE-RES-16K
    11. 10788
    Prev
    Next
    INDEX
    Explanations

    comments or comment-like structures in code

    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
    ReusableCell
    -0.75
    NameInMap
    -0.70
     SearchView
    -0.69
     Efq
    -0.68
    šanai
    -0.66
    bcryptjs
    -0.65
     Majefty
    -0.64
    XmlAccessorType
    -0.63
     StringField
    -0.63
    页面存档备份
    -0.62
    POSITIVE LOGITS
    PhysRev
    0.58
     VIAF
    0.52
     Harlan
    0.49
     underlying
    0.48
     once
    0.48
     Picchu
    0.48
    abh
    0.47
    ypep
    0.47
    vistar
    0.47
     fully
    0.46
    Activations Density 0.113%

    No Known Activations