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. 21-GEMMASCOPE-RES-16K
    6. 12568
    Prev
    Next
    INDEX
    Explanations

    references to financial assistance or benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ExecuteAsync
    -0.62
    posedge
    -0.61
    ConstraintMaker
    -0.60
     stabilisation
    -0.58
     OBO
    -0.57
     esternos
    -0.56
    Ещё
    -0.56
     characterised
    -0.55
     şi
    -0.52
    Pulitzer
    -0.51
    POSITIVE LOGITS
    -£
    0.62
     Scottish
    0.60
     Scotland
    0.58
    nhs
    0.58
    tigny
    0.58
     VAT
    0.57
     £
    0.57
    Scottish
    0.56
    Scotland
    0.56
    vaux
    0.56
    Activations Density 0.254%

    No Known Activations