© 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. 10-GEMMASCOPE-RES-16K
    11. 6043
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transition words indicative of causal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ècie
    -0.86
    :✨
    -0.77
     AssemblyCulture
    -0.72
     kaarangay
    -0.70
    épendance
    -0.68
    openConnection
    -0.67
     feroit
    -0.67
     pleaſure
    -0.67
    lgari
    -0.66
     propOrder
    -0.66
    POSITIVE LOGITS
     also
    1.17
    also
    0.78
     ALSO
    0.78
     też
    0.73
     Also
    0.73
     также
    0.71
     también
    0.69
    Also
    0.67
     także
    0.66
     também
    0.63
    Activations Density 1.193%

    No Known Activations