© 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. 4-GEMMASCOPE-RES-16K
    11. 10867
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "To" indicating purpose or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usstsein
    -0.69
    endpush
    -0.69
    $.
    -0.67
    AndEndTag
    -0.66
    İstinadlar
    -0.64
    ImageContext
    -0.63
    ^(@)
    -0.62
    \]
    -0.61
    GenerationType
    -0.61
     useParams
    -0.61
    POSITIVE LOGITS
    To
    1.52
     To
    1.47
     TO
    0.89
    to
    0.86
    TO
    0.80
     Toh
    0.75
     Чтобы
    0.70
    Чтобы
    0.68
    For
    0.66
    MigrationBuilder
    0.65
    Activations Density 0.192%

    No Known Activations