© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 729
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to user interface components and events

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

    references to date and time-related user interface elements in programming contexts

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    setContentView
    -0.63
    TabIndex
    -0.55
    Ljava
    -0.54
     varargin
    -0.54
     UITableViewCell
    -0.48
     argv
    -0.48
    ktır
    -0.48
     InputDecoration
    -0.47
     UIImageView
    -0.46
    Rohy
    -0.46
    POSITIVE LOGITS
     listener
    0.77
     समीक्षाओं
    0.67
    ClickListener
    0.65
    CompleteListener
    0.64
    ErrorListener
    0.61
     consulter
    0.60
     Listener
    0.60
    Listener
    0.60
    ">//
    0.58
    listener
    0.58
    Activations Density 0.017%

    No Known Activations