© 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. 66159
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals associated with political or financial controversies

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

    Marcos Valério, Vittorio Alfieri

    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
    REB
    -0.57
     Ebert
    -0.56
     дописавши
    -0.54
    bbbb
    -0.54
    bby
    -0.54
    Hamb
    -0.54
     nb
    -0.54
    ubble
    -0.54
     hb
    -0.53
    bbb
    -0.52
    POSITIVE LOGITS
    yorsunuz
    0.52
     Yoshida
    0.49
     Wirkungen
    0.47
     feroit
    0.47
    setMode
    0.46
     Willi
    0.46
    attaque
    0.45
    eningen
    0.45
     Daley
    0.45
     StringIO
    0.44
    Activations Density 0.282%

    No Known Activations