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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4105
    Prev
    Next
    INDEX
    Explanations

    sequences of hash symbols used for referencing or citations

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

    catalog numbers after hash

    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
    <h3>
    -0.52
    <em>
    -0.48
    <blockquote>
    -0.48
    <b>
    -0.43
    <i>
    -0.43
    <strong>
    -0.42
     Levin
    -0.40
     can
    -0.40
     se
    -0.40
     pop
    -0.39
    POSITIVE LOGITS
     \#
    1.47
    \#
    1.38
     $\#
    1.13
    \#:
    1.11
    \#\#
    1.11
     \#:
    1.09
    $\#
    0.99
    #\
    0.77
     #:
    0.72
    EndInit
    0.71
    Activations Density 0.015%

    No Known Activations