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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6801
    Prev
    Next
    INDEX
    Explanations

    significant moments and their impact within narratives

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

    "moment" or "moments"

    np_acts-logits-general · gemini-2.0-flash

    moment functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     agrícolas
    -0.36
     lastik
    -0.34
    cidae
    -0.34
    matig
    -0.33
    vlád
    -0.33
    ştır
    -0.33
     tých
    -0.33
     civiles
    -0.33
     Gewer
    -0.33
    ถม
    -0.32
    POSITIVE LOGITS
     moment
    2.25
    moment
    2.20
    Moment
    2.11
     Moment
    2.08
     moments
    2.06
    moments
    1.95
     Moments
    1.91
     MOMENT
    1.91
    Moments
    1.90
     Momente
    1.64
    Activations Density 0.121%

    No Known Activations