© 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. 118642
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate emotional expression and reflective sentiment

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

    We have decided to grant police office

    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
    Identyfik
    -0.54
    
    -0.52
    cism
    -0.52
    Архівовано
    -0.52
     désolés
    -0.50
    ܃
    -0.49
    ंदीखरीदारी
    -0.49
    phor
    -0.49
    جغرافيا
    -0.48
    vides
    -0.48
    POSITIVE LOGITS
     "../../../
    0.34
     ब्रेकडाउन
    0.32
    subpackage
    0.32
    CopyWith
    0.31
    -------------</
    0.31
    VolleyError
    0.30
     NUKAT
    0.30
    ="../
    0.30
     onCancelled
    0.29
     Públicas
    0.28
    Activations Density 0.007%

    No Known Activations