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. 23-GEMMASCOPE-RES-16K
    6. 5705
    Prev
    Next
    INDEX
    Explanations

    elements related to advertisements and promotional content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     JpaRepository
    -0.82
    DMETHOD
    -0.74
     թվական
    -0.70
    __*/
    -0.69
    astéroïdes
    -0.69
    تفصیلات
    -0.69
    <()>
    -0.68
     initWithFrame
    -0.68
    Fazit
    -0.67
     GenerationType
    -0.67
    POSITIVE LOGITS
    View
    0.75
     View
    0.75
     view
    0.71
    Share
    0.71
    Return
    0.70
    Close
    0.68
    Search
    0.68
     Share
    0.68
     Return
    0.68
     »
    0.68
    Activations Density 0.737%

    No Known Activations