© 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. 126921
    Prev
    Next
    INDEX
    Explanations

    statements indicating findings or results from research or studies

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

    investigation and reporting verbs

    np_acts-logits-general · gemini-2.5-flash-lite

    sentences or phrases containing formal academic/action verbs that report findings, assessments, determinations, or other research/methodological actions.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     arşivlendi
    -0.56
     Audiodateien
    -0.55
     خارجية
    -0.52
     propOrder
    -0.51
    ArgumentParser
    -0.51
     оригіналу
    -0.50
     MainAxisSize
    -0.49
     مشين
    -0.49
     initComponents
    -0.48
     doInBackground
    -0.48
    POSITIVE LOGITS
     otomatig
    0.36
    klaim
    0.35
     Италијани
    0.35
    autant
    0.34
    uch
    0.32
     Numerade
    0.32
    adalajara
    0.31
    nak
    0.31
    its
    0.31
     pinta
    0.31
    Activations Density 0.850%

    No Known Activations