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. 20-GEMMASCOPE-RES-16K
    6. 2212
    Prev
    Next
    INDEX
    Explanations

    narratives or stories that convey personal experiences and insights

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

    Tokens preceding/related to "story" or "stories."

    np_acts-logits-general · gemini-2.0-flash

    story or stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     تضيفلها
    -0.64
    riff
    -0.53
    DispatchToProps
    -0.51
    Населення
    -0.51
    fieldId
    -0.51
    ulás
    -0.50
    DockStyle
    -0.49
    tvguidetime
    -0.48
    pielen
    -0.48
    Nuorodos
    -0.47
    POSITIVE LOGITS
     story
    3.30
     stories
    2.90
    story
    2.76
    Story
    2.71
     Story
    2.67
     STORY
    2.61
    stories
    2.45
    Stories
    2.39
    STORY
    2.39
     Stories
    2.38
    Activations Density 0.297%

    No Known Activations