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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9100
    Prev
    Next
    INDEX
    Explanations

    references to "Star" or the term "Stars" in various contexts

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

    mentions of "Star Wars" and other pop culture franchises.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    references to Star Wars and Star Trek franchises.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jeografia
    -0.35
    ppure
    -0.34
    heses
    -0.33
     leisten
    -0.33
     wund
    -0.31
    ی
    -0.31
    Preparación
    -0.31
     Alltag
    -0.31
     feiner
    -0.31
    oncé
    -0.30
    POSITIVE LOGITS
     Star
    0.96
    Star
    0.94
     star
    0.91
     STAR
    0.84
    STAR
    0.83
    star
    0.82
     Stars
    0.80
     🌟
    0.78
     Starlight
    0.75
     Wars
    0.74
    Activations Density 0.235%

    No Known Activations