© 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. 16-GEMMASCOPE-RES-16K
    11. 1255
    Prev
    Next
    INDEX
    Explanations

    phrases or concepts that emphasize an element of specificity or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "That" followed by various words

    np_acts-logits-general · gemini-2.0-flash

    that followed by adjective or noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ainfi
    -0.61
     préféré
    -0.60
    styleUrls
    -0.59
     myſelf
    -0.56
     marié
    -0.53
     autant
    -0.52
     respectivement
    -0.52
     ragioni
    -0.52
     originaire
    -0.51
    //
    -0.51
    POSITIVE LOGITS
     pesky
    0.82
     big
    0.66
     Rukh
    0.64
     final
    0.63
     elusive
    0.61
     '\\;'
    0.61
    Jeografia
    0.59
     Walkover
    0.58
    的那
    0.57
     darn
    0.57
    Activations Density 0.124%

    No Known Activations