© 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. 15918
    Prev
    Next
    INDEX
    Explanations

    start tokens and significant identifiers in structured data

    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
    țiile
    -0.48
     Meksiku
    -0.44
    GOTREF
    -0.41
    anthes
    -0.39
    gisayar
    -0.39
     thought
    -0.39
     peix
    -0.39
     sensu
    -0.38
    本線
    -0.37
     COPYRIGHT
    -0.37
    POSITIVE LOGITS
    Rhestr
    1.05
    ########.
    0.89
    rungsseite
    0.76
     TextInputType
    0.73
    IndentedString
    0.69
    WriteLiteral
    0.68
     تضيفلها
    0.68
     الحره
    0.67
    Enllaces
    0.66
    Koordinaten
    0.66
    Activations Density 0.429%

    No Known Activations