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. 13718
    Prev
    Next
    INDEX
    Explanations

    complex character interactions and narratives that explore deeper themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    •Literature
    complex character interactions and narratives that explore deeper themes

    No Comments

    Negative Logits
    LookAnd
    -0.72
     يتيمه
    -0.70
    RTEE
    -0.68
     Infórmanos
    -0.65
    出版年
    -0.65
     Exacts
    -0.65
    Datuak
    -0.64
    FunctionFlags
    -0.63
    tvguidetime
    -0.63
    ScopeManager
    -0.62
    POSITIVE LOGITS
     plot
    1.97
     storyline
    1.76
     story
    1.67
     storylines
    1.58
     narrative
    1.56
    plot
    1.54
     Plot
    1.43
     PLOT
    1.42
     plots
    1.42
    story
    1.39
    Activations Density 0.680%

    No Known Activations