Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 77106
    Prev
    Next
    INDEX
    Explanations

    patterns or structures related to regular expressions (regex)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ParallelGroup
    -0.57
    autorest
    -0.56
     ब्रेकडाउन
    -0.55
     avoient
    -0.54
    новништво
    -0.53
     sumpay
    -0.53
    ArgumentParser
    -0.52
    canestro
    -0.51
     åt
    -0.50
    UnitTesting
    -0.50
    POSITIVE LOGITS
    ?:
    0.82
    (?:
    0.60
     ?:
    0.56
    ?;
    0.52
    ()?;
    0.51
    /?
    0.51
    ?,?,
    0.49
    ()?.
    0.48
    elif
    0.48
    ?.
    0.47
    Activations Density 0.001%

    No Known Activations