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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 101489
    Prev
    Next
    INDEX
    Explanations

    definitions and descriptions of programming constructs or functions

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

    ((x) << constant)

    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
     mainly
    -0.35
    k
    -0.31
     par
    -0.31
    ken
    -0.31
     especially
    -0.31
     k
    -0.30
     mostly
    -0.30
     einige
    -0.30
     couple
    -0.30
     primarily
    -0.30
    POSITIVE LOGITS
    rungsseite
    1.02
     محفوظة
    0.75
    SequentialGroup
    0.73
     desmotivaciones
    0.70
    PerformLayout
    0.69
    StoreMessageInfo
    0.66
     CURIAM
    0.66
    点此举报
    0.65
    tonode
    0.63
    ValueStyle
    0.63
    Activations Density 0.091%

    No Known Activations