© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 81477
    Prev
    Next
    INDEX
    Explanations

    code-related terms that denote string manipulation or extraction functions

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

    substr and related words

    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
     McManus
    -0.39
     renda
    -0.39
     Towne
    -0.38
     é
    -0.38
     Gene
    -0.37
     atraer
    -0.37
     EMERGENCY
    -0.37
     emergency
    -0.37
     and
    -0.36
    Gene
    -0.36
    POSITIVE LOGITS
    substr
    2.61
     substr
    2.39
     substrates
    1.25
     substrate
    1.25
    substrate
    1.23
     Substrate
    1.13
    Substrate
    1.09
     суб
    0.73
    subst
    0.71
    SequentialGroup
    0.69
    Activations Density 0.001%

    No Known Activations