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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 4234
    Prev
    Next
    INDEX
    Explanations

    references to social dynamics and community engagement

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

    Something is visible to someone

    np_acts-logits-general · gemini-2.0-flash

    people present and observing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ėjimo
    -0.55
     recommandons
    -0.51
    ⓧ
    -0.50
    yarnpkg
    -0.47
     jemand
    -0.46
    porre
    -0.46
     astore
    -0.46
    eseorang
    -0.46
     ?>/
    -0.45
     uits
    -0.45
    POSITIVE LOGITS
     onlookers
    0.73
    windowFixed
    0.71
     audiences
    0.70
    schild
    0.70
     spectators
    0.66
     passers
    0.64
     viewers
    0.63
     peers
    0.63
     FetchType
    0.59
    TintMode
    0.57
    Activations Density 0.230%

    No Known Activations