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-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16151
    Prev
    Next
    INDEX
    Explanations

    references to legal or judicial issues involving individuals and their actions

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

    followed by "for" or similar prepositions

    np_acts-logits-general · gemini-2.0-flash

    month, trip, assault, telephone, Aging, Domain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gereja
    -0.36
     rumahnya
    -0.34
     doğum
    -0.34
     Njema
    -0.34
     sähkö
    -0.34
     ifrån
    -0.34
     christlichen
    -0.33
     hujan
    -0.32
     Wassers
    -0.32
     alguno
    -0.32
    POSITIVE LOGITS
    MigrationBuilder
    1.05
     betweenstory
    0.89
    WebElementEntity
    0.85
    tagHelperRunner
    0.79
     ब्रेकडाउन
    0.78
     című
    0.77
     становника
    0.69
    matchCondition
    0.69
     scenario
    0.67
    RectangleBorder
    0.67
    Activations Density 1.373%

    No Known Activations