© 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. 3-GEMMASCOPE-RES-16K
    11. 11673
    Prev
    Next
    INDEX
    Explanations

    phrases indicating compatibility or pairings between items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.55
    NamedQuery
    -0.54
    IsMutable
    -0.51
    zzleHttp
    -0.51
     defaultstate
    -0.49
    tero
    -0.49
    tubers
    -0.47
    enschappelijke
    -0.47
     credere
    -0.47
    psons
    -0.46
    POSITIVE LOGITS
     fitting
    0.79
     Fitting
    0.77
     complemento
    0.75
     Fits
    0.73
    suited
    0.71
     complements
    0.70
    Fitting
    0.70
    complement
    0.69
    compatibility
    0.69
    suitable
    0.69
    Activations Density 0.530%

    No Known Activations