© 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. 31-GEMMASCOPE-RES-131K
    11. 24111
    Prev
    Next
    INDEX
    Explanations

    statistical assessment metrics related to data analysis and experimental design

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

    creating and producing scientific materials

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    XmlAccessorType
    -0.63
    PerformLayout
    -0.54
     hikariConfig
    -0.52
     pinulongan
    -0.51
    arraycopy
    -0.50
    Autoritní
    -0.49
    $_['
    -0.49
     للمعارف
    -0.49
    UnitTesting
    -0.48
    niająca
    -0.48
    POSITIVE LOGITS
     creation
    1.32
     manufacture
    1.30
    制作
    1.28
     pembuatan
    1.23
    作成
    1.21
    製作
    1.20
     constructing
    1.16
     fabriquer
    1.09
     elaboración
    1.08
     constructed
    1.07
    Activations Density 0.562%

    No Known Activations