© 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. 7-GEMMASCOPE-RES-16K
    11. 4889
    Prev
    Next
    INDEX
    Explanations

    underscore-prefixed variable names

    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
    Rüyada
    -1.08
    WithIOException
    -0.82
    GEBURTSDATUM
    -0.81
    InitVars
    -0.81
    üyada
    -0.80
    Vidite
    -0.80
    IVEREF
    -0.80
    addCriterion
    -0.79
    elemField
    -0.78
    messageInfo
    -0.77
    POSITIVE LOGITS
    ↵↵
    0.65
     There
    0.58
    ↵
    0.57
    mathrm
    0.57
     It
    0.57
    There
    0.55
    [toxicity=0]
    0.53
    It
    0.52
     This
    0.52
     isn
    0.51
    Activations Density 0.084%

    No Known Activations