© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 8969
    Prev
    Next
    INDEX
    Explanations

    statements or clauses that present examples or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BorderRadius
    -0.70
     nargin
    -0.62
    figsize
    -0.62
     lenker
    -0.61
    closedir
    -0.58
    protoimpl
    -0.57
     już
    -0.51
    sendRedirect
    -0.51
    IntoConstraints
    -0.50
    amaño
    -0.49
    POSITIVE LOGITS
    createTextNode
    0.79
    setVerticalGroup
    0.70
    fillText
    0.68
    WriteLiteral
    0.68
     phrases
    0.63
     saying
    0.62
     words
    0.61
    ว่า
    0.60
     demografica
    0.59
     resourceCulture
    0.57
    Activations Density 0.510%

    No Known Activations