© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 7956
    Prev
    Next
    INDEX
    Explanations

    technical descriptions related to semiconductor devices and their construction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACHUSET
    -0.76
    twimg
    -0.72
    givers
    -0.71
    :✨
    -0.71
     surla
    -0.69
    opsida
    -0.67
    AILED
    -0.66
    culoskeletal
    -0.65
    ousal
    -0.65
     Scherer
    -0.65
    POSITIVE LOGITS
     età
    0.50
     jspb
    0.48
     således
    0.43
     voorzien
    0.43
    PrototypeOf
    0.42
    A
    0.41
     Tally
    0.40
     disposto
    0.40
     Figs
    0.40
     mukaan
    0.40
    Activations Density 0.363%

    No Known Activations