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. 6-GEMMASCOPE-RES-16K
    6. 2541
    Prev
    Next
    INDEX
    Explanations

    import statements used for loading components and dependencies in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NOPQRST
    -0.77
     itſelf
    -0.76
     Efq
    -0.76
     Monfieur
    -0.75
     myſelf
    -0.71
     ModelRenderer
    -0.68
     tramont
    -0.67
     betweenstory
    -0.67
    utnik
    -0.66
     himſelf
    -0.66
    POSITIVE LOGITS
    RegistryLite
    0.61
     rgba
    0.52
    rgba
    0.52
    InjectAttribute
    0.49
    ]^{-
    0.49
     anglès
    0.48
    GNUC
    0.48
    <eos>
    0.47
     gql
    0.47
    theil
    0.47
    Activations Density 0.019%

    No Known Activations