© 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. 23-GEMMASCOPE-RES-16K
    11. 12655
    Prev
    Next
    INDEX
    Explanations

    locations and place names, particularly in New Zealand and Australia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Judas
    -0.52
    messageInfo
    -0.51
     BorderRadius
    -0.50
    pgterms
    -0.49
    stylers
    -0.47
    Уважа
    -0.46
    endphp
    -0.45
     Drapeau
    -0.45
     Judas
    -0.45
     saurait
    -0.45
    POSITIVE LOGITS
     Gold
    0.95
    Gold
    0.85
     gold
    0.73
     Ball
    0.72
     GOLD
    0.71
     Wag
    0.69
    gold
    0.68
     Mand
    0.65
     Towns
    0.64
     Sub
    0.64
    Activations Density 0.148%

    No Known Activations