© 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. 39115
    Prev
    Next
    INDEX
    Explanations

    elements related to interpersonal communication and relationships

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

    names and titles

    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
    fjspx
    -0.73
     snippetHide
    -0.66
    帖最后由
    -0.65
    PMailer
    -0.64
    tagext
    -0.63
    protoimpl
    -0.60
    GEBURTSDATUM
    -0.59
    oa̍t
    -0.59
    Vidite
    -0.58
    IVEREF
    -0.58
    POSITIVE LOGITS
     têtes
    0.35
     burn
    0.35
    Notae
    0.35
    Display
    0.34
    cabeza
    0.33
    utriche
    0.33
     vš
    0.33
    wo
    0.33
    rodz
    0.33
     curly
    0.32
    Activations Density 0.075%

    No Known Activations