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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 699
    Prev
    Next
    INDEX
    Explanations

    various types of punctuation and conjunctions that indicate sentence structure and flow

    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
    BagLayout
    -0.47
    surate
    -0.47
    المناصب
    -0.44
     edelstahl
    -0.43
     transférez
    -0.43
    matchCondition
    -0.43
    ⏜
    -0.42
    mainAxisSize
    -0.42
     Grüße
    -0.41
    Véxase
    -0.41
    POSITIVE LOGITS
    DockStyle
    0.49
    InitVars
    0.39
    univer
    0.39
    HandlerContext
    0.38
     виправивши
    0.38
    jednoc
    0.37
    |')
    0.37
    che
    0.36
    ngdoc
    0.36
    RegressionTest
    0.35
    Activations Density 0.091%

    No Known Activations