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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17-GEMMASCOPE-RES-16K
    6. 13219
    Prev
    Next
    INDEX
    Explanations

    connections to various contexts of actions and observations involving people and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISODE
    -0.63
    eabouts
    -0.60
    🏻‍♀️
    -0.59
    raits
    -0.59
    UMNS
    -0.58
    onnay
    -0.58
    betic
    -0.58
    ‍♀️
    -0.58
    ORAGE
    -0.57
    ‍♂️
    -0.57
    POSITIVE LOGITS
     tonight
    0.72
     today
    0.70
     domani
    0.67
     tomorrow
    0.67
    Personendaten
    0.66
     Paglinawan
    0.62
     yesterday
    0.57
     ieri
    0.57
     Chwiliwch
    0.56
     nowadays
    0.56
    Activations Density 0.779%

    No Known Activations