© 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. 31227
    Prev
    Next
    INDEX
    Explanations

    the word "man" in various contexts

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

    Hausman, Rodman, Chernozhukov

    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
    OGND
    -0.59
     AssemblyVersion
    -0.48
    cauc
    -0.48
    kilde
    -0.46
     esboço
    -0.46
     Scu
    -0.46
     '\\;'
    -0.46
     Kü
    -0.45
     excite
    -0.45
    iyaki
    -0.45
    POSITIVE LOGITS
    man
    2.44
    MAN
    1.92
     man
    1.62
    Man
    1.54
    マン
    1.29
     Man
    1.28
    mans
    1.26
     MAN
    1.23
    ман
    1.15
    mann
    1.13
    Activations Density 0.023%

    No Known Activations