Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 117337
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional distress and creativity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    orsese
    -0.52
     Infórmanos
    -0.49
    Abitanti
    -0.47
    PathVariable
    -0.46
     Reſ
    -0.45
    NewLabel
    -0.44
     estekak
    -0.44
     similarly
    -0.44
    skjaer
    -0.44
     مرئيه
    -0.44
    POSITIVE LOGITS
    WriteTagHelper
    0.43
    AddTagHelper
    0.36
    ConstraintMaker
    0.35
    Алек
    0.35
    UnusedPrivate
    0.35
    Демографія
    0.33
    DBNull
    0.33
    Acab
    0.32
    ValueStyle
    0.32
    migrationBuilder
    0.32
    Activations Density 0.013%

    No Known Activations