© 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. 102535
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Sally" and the location "Bristol."

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

    Sally and Bristol 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
     Creat
    -0.61
    存于互联网档案馆
    -0.61
    timeFormat
    -0.59
     Chaudh
    -0.59
    ranean
    -0.58
    FunctionFlags
    -0.57
    <blockquote>
    -0.56
     Aqu
    -0.56
     BUILD
    -0.55
     FER
    -0.55
    POSITIVE LOGITS
     Partei
    0.61
     Nacionales
    0.58
    i
    0.58
     Occidente
    0.55
     paleta
    0.54
     Schwester
    0.54
     Sorge
    0.54
     fileSize
    0.53
     Umfang
    0.53
     Tochter
    0.53
    Activations Density 0.022%

    No Known Activations