© 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. 20-GEMMASCOPE-RES-131K
    11. 80367
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals and places

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

    Stephanie, Jonathan, Patterson, names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    miR
    -0.48
    scroll
    -0.44
     ioutil
    -0.44
     Dalai
    -0.41
    sci
    -0.40
    IL
    -0.40
     ältere
    -0.39
    s
    -0.39
    Jes
    -0.39
    step
    -0.38
    POSITIVE LOGITS
     Patterson
    0.72
    fortawesome
    0.67
     Tiffany
    0.65
     Bowman
    0.65
    ation
    0.64
    alisation
    0.64
     Davidson
    0.63
     Crawford
    0.63
     Stephanie
    0.62
    nolia
    0.62
    Activations Density 0.032%

    No Known Activations