© 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. 61286
    Prev
    Next
    INDEX
    Explanations

    references to assertion methods and query string handling in code

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

    assertions and query strings

    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
     זאת
    -0.46
     krep
    -0.35
     yoktur
    -0.35
     Küste
    -0.34
     normalidad
    -0.33
     etk
    -0.32
     hechos
    -0.32
     Sénat
    -0.31
     Deshalb
    -0.30
     moks
    -0.30
    POSITIVE LOGITS
    tableFuture
    0.85
    ThroughAttribute
    0.77
     assert
    0.73
    RRect
    0.73
    assert
    0.71
    <unused79>
    0.69
    <unused43>
    0.69
    AnchorStyles
    0.69
    <unused14>
    0.69
    <unused8>
    0.69
    Activations Density 0.002%

    No Known Activations