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. 52540
    Prev
    Next
    INDEX
    Explanations

    programming constructs and operations related to array manipulation and data processing

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

    data filtering and manipulation

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ftagPool
    -0.47
     незавершена
    -0.46
    tonode
    -0.41
    RTLI
    -0.37
     wireType
    -0.36
     design
    -0.32
    ragamo
    -0.32
     адре
    -0.31
    leder
    -0.30
    addView
    -0.30
    POSITIVE LOGITS
    setupUi
    0.60
    
    0.51
    rungsseite
    0.49
    basicConfig
    0.47
     consolidation
    0.45
    GHIJKLM
    0.45
     Consolidation
    0.44
    modelBuilder
    0.44
    createServer
    0.43
    Население
    0.42
    Activations Density 0.013%

    No Known Activations