Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 103080
    Prev
    Next
    INDEX
    Explanations

    personal pronouns, particularly "I" and "you," indicating a focus on individual experiences and perspectives

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

    The token "I" at the beginning of a sentence or clause where someone is introducing their personal opinion or perspective.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     समीक्षाओं
    -0.56
    niająca
    -0.53
    Jeografia
    -0.52
    RTSC
    -0.52
    StructEnd
    -0.49
    󠁴
    -0.47
     jspb
    -0.47
    protoimpl
    -0.47
    parsedMessage
    -0.47
    bewerken
    -0.46
    POSITIVE LOGITS
    backslash
    0.40
    ยนต์
    0.36
     thoughts
    0.34
     suggestions
    0.33
     obje
    0.33
     judging
    0.33
     näh
    0.33
     comunidades
    0.33
     intéressant
    0.33
     impati
    0.33
    Activations Density 0.091%

    No Known Activations