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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 9490
    Prev
    Next
    INDEX
    Explanations

    mentions of popular films and film-related terms

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

    first-person subjective statements expressing the writer's opinions, preferences, or list-making (e.g., "I", "I'm", "I'll", "my", "picks", "list", "include").

    oai_token-act-pair · gpt-5-miniTriggered by @phamvanluong2003
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.72
    expandindo
    -0.65
    AndEndTag
    -0.60
     InputDecoration
    -0.54
    dotenv
    -0.52
    >*/
    -0.52
    urlopen
    -0.51
    edoria
    -0.51
    /−
    -0.51
    erapeu
    -0.49
    POSITIVE LOGITS
    Selection
    0.57
     تضيفلها
    0.57
     selections
    0.56
     favorites
    0.55
     selection
    0.53
     Selection
    0.52
    SELECTION
    0.51
     SELECTION
    0.51
     answer
    0.51
     Auswahl
    0.50
    Activations Density 0.171%

    No Known Activations