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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 91488
    Prev
    Next
    INDEX
    Explanations

    descriptive elements related to costumes and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    MigrationBuilder
    -0.47
    Captor
    -0.43
     putus
    -0.38
     faibles
    -0.38
    acamole
    -0.37
     exécu
    -0.37
    avadoc
    -0.36
     telur
    -0.36
    Tests
    -0.36
     mathématiques
    -0.36
    POSITIVE LOGITS
     виправивши
    0.60
     disambiguazione
    0.58
    GEBURTSDATUM
    0.55
    ftagPool
    0.51
    uxxxx
    0.51
     surla
    0.49
    ValueStyle
    0.46
     Савезне
    0.46
     AppCompatTheme
    0.45
    󠁣
    0.45
    Activations Density 0.024%

    No Known Activations