© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105658
    Prev
    Next
    INDEX
    Explanations

    pronouns used in the context of relationships or emotional experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     Mehrheit
    -0.39
     tarko
    -0.38
     jät
    -0.36
     föres
    -0.34
     razón
    -0.34
    6
    -0.34
    qwerty
    -0.32
    foque
    -0.32
     Glaube
    -0.32
     teoría
    -0.32
    POSITIVE LOGITS
     until
    0.79
    帖最后由
    0.78
    uxxxx
    0.78
     Until
    0.75
    until
    0.73
    Until
    0.73
     ویکی‌پدی
    0.70
     <<<<<<<<<<<<<<
    0.69
    IVEREF
    0.68
     untill
    0.67
    Activations Density 0.013%

    No Known Activations