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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 76631
    Prev
    Next
    INDEX
    Explanations

    occurrences of the curly brace character

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

    mathematical and structured text

    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
    -0.88
    URLException
    -0.88
    InitVars
    -0.84
     NSCoder
    -0.84
    IntoConstraints
    -0.83
    iſen
    -0.83
    parsedMessage
    -0.82
    ſchaft
    -0.81
    ConstraintMaker
    -0.80
     Autorisations
    -0.80
    POSITIVE LOGITS
    {
    0.69
    _{
    0.55
     {
    0.53
    (
    0.51
    <td>
    0.50
    <em>
    0.49
    <i>
    0.47
     of
    0.45
     my
    0.44
    }{
    0.43
    Activations Density 0.119%

    No Known Activations