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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 19741
    Prev
    Next
    INDEX
    Explanations

    key programming terms and syntax elements relevant to graphics and data types in code

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

    technical terms and libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.40
    AuthGuard
    -0.32
     bil
    -0.31
    putExtra
    -0.31
    SourceChecksum
    -0.30
     Hutchins
    -0.30
     ubicada
    -0.30
    anceled
    -0.29
    ToAction
    -0.29
     Kjell
    -0.29
    POSITIVE LOGITS
    mybatisplus
    1.84
    hbase
    1.22
    vaadin
    1.17
    setVerticalGroup
    1.16
    GraphicsUnit
    1.11
     تكبرها
    1.09
     BoxDecoration
    0.98
    IntoConstraints
    0.87
    ChildScrollView
    0.80
    ::_('
    0.78
    Activations Density 0.001%

    No Known Activations