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

    Neuronpedia

    Jacobian LensNEW
    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. 52429
    Prev
    Next
    INDEX
    Explanations

    phrases expressing consistency or frequency in actions or thoughts

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

    always + verb sequences

    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
     SUD
    -0.35
    subpackage
    -0.35
     الحره
    -0.34
    tanleria
    -0.33
    Handlung
    -0.33
     Gattung
    -0.33
    ycznych
    -0.32
    Doch
    -0.31
    SUD
    -0.31
    huset
    -0.29
    POSITIVE LOGITS
     always
    0.91
     Always
    0.89
    always
    0.89
    Always
    0.88
     selalu
    0.83
     zawsze
    0.82
    awsze
    0.81
     Siempre
    0.80
    siempre
    0.78
     alway
    0.77
    Activations Density 0.012%

    No Known Activations