© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 64888
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to cardiovascular risk factors and metabolic disorders

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

    age-related macular degeneration

    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
     Gesells
    -0.39
     bautizo
    -0.36
     bero
    -0.34
     rowing
    -0.33
     donor
    -0.30
     tatuaje
    -0.30
     Komunikasi
    -0.30
     beauty
    -0.29
     brandy
    -0.29
     baking
    -0.29
    POSITIVE LOGITS
     resourceCulture
    0.66
    ValueStyle
    0.65
    Personensuche
    0.65
     &___
    0.65
    Fol
    0.60
    帖最后由
    0.59
    tagHelperRunner
    0.58
    featureID
    0.57
     ब्रेकडाउन
    0.55
    ----</
    0.55
    Activations Density 0.268%

    No Known Activations