© 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. 55661
    Prev
    Next
    INDEX
    Explanations

    words that signify precision and detail in descriptions or arguments

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

    precisely, exactly

    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
     ferons
    -0.39
    サイズは
    -0.36
    UpdateCommand
    -0.35
    told
    -0.35
     troup
    -0.34
     ister
    -0.34
    InsertCommand
    -0.34
    及び
    -0.34
    สุ
    -0.34
     kal
    -0.34
    POSITIVE LOGITS
     именно
    1.28
     саме
    1.20
     Именно
    1.16
     właśnie
    1.08
     právě
    1.02
     juist
    0.94
     juuri
    0.93
     justru
    0.81
     Gerade
    0.78
     gerade
    0.75
    Activations Density 0.009%

    No Known Activations