© 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. 128598
    Prev
    Next
    INDEX
    Explanations

    key phrases indicating planned actions, assessments, or outcomes related to meetings and evaluations

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

    revealing key findings

    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
     nakalista
    -0.59
    
    -0.51
     Geſch
    -0.51
    AddTagHelper
    -0.49
     Händen
    -0.45
    évaluateur
    -0.44
     gyhoeddwyd
    -0.43
    majánló
    -0.42
     Nähe
    -0.42
    ultados
    -0.42
    POSITIVE LOGITS
    UnusedPrivate
    0.56
    ::_('
    0.49
    ISupport
    0.42
    LookAnd
    0.40
    colnshire
    0.36
    setVerticalGroup
    0.36
    withIdentifier
    0.36
    revalidate
    0.35
     кори
    0.35
     hende
    0.35
    Activations Density 0.229%

    No Known Activations