© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 93201
    Prev
    Next
    INDEX
    Explanations

    Java types and class definitions related to identifiers and data types

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

    programming data types

    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
     betweenstory
    -0.79
     يتيمه
    -0.78
    AndEndTag
    -0.76
    RegressionTest
    -0.71
    UrlResolution
    -0.71
     ModelExpression
    -0.71
    localctx
    -0.65
    StoryboardSegue
    -0.65
    SharedCtor
    -0.64
    IsContent
    -0.60
    POSITIVE LOGITS
     principalmente
    0.38
     Standort
    0.38
     spørsmål
    0.34
     royaume
    0.31
    CDCl
    0.30
     deleteById
    0.30
     sobretudo
    0.30
    Szia
    0.29
    primarily
    0.28
     primarily
    0.28
    Activations Density 0.003%

    No Known Activations