© 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. 117944
    Prev
    Next
    INDEX
    Explanations

    terms related to specific frameworks, structures, and categorizations in research and healthcare contexts

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

    breaking into situations

    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
    </strong>
    -0.34
     nincs
    -0.33
     person
    -0.33
     reine
    -0.31
    Ligações
    -0.31
     warring
    -0.31
     origines
    -0.31
    keiten
    -0.31
     complejo
    -0.30
     appels
    -0.30
    POSITIVE LOGITS
     surla
    0.73
     ujednoznacz
    0.73
    ThroughAttribute
    0.68
     JpaRepository
    0.66
     autorytatywna
    0.61
    UnifiedTopology
    0.61
    VersionUID
    0.60
    ☸
    0.60
     initComponents
    0.59
     arşivlendi
    0.58
    Activations Density 0.185%

    No Known Activations