© 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. 20-GEMMASCOPE-RES-131K
    6. 66406
    Prev
    Next
    INDEX
    Explanations

    topics and references related to African American studies and history

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

    American studies, history, scholarship

    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
    findpost
    -0.66
    eynman
    -0.56
    styleUrls
    -0.44
    nhs
    -0.44
    Kirchen
    -0.40
    piram
    -0.40
     skin
    -0.40
    pcb
    -0.40
    COUVER
    -0.39
    XmlAccessType
    -0.38
    POSITIVE LOGITS
     Мексичка
    0.54
    Personensuche
    0.50
     subjects
    0.44
     topics
    0.44
     kartą
    0.43
    Biografie
    0.42
     betrek
    0.42
     scholarship
    0.41
     resourceCulture
    0.41
    CLAS
    0.41
    Activations Density 0.017%

    No Known Activations