© 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. 12393
    Prev
    Next
    INDEX
    Explanations

    subcategories of empty tokens or placeholders in code fragments

    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
     Мексичка
    -0.70
    IsMutable
    -0.66
    webElement
    -0.66
    Obrázky
    -0.65
    الإنجليزية
    -0.62
     Pfal
    -0.61
    principalColumn
    -0.61
     Jwt
    -0.60
     /\.(
    -0.59
    NegativeButton
    -0.58
    POSITIVE LOGITS
     intptr
    0.67
     henvisninger
    0.61
    Referencer
    0.56
    BeginContext
    0.55
    ագրություններ
    0.53
    CodeAttribute
    0.51
    ఔ
    0.50
     FUNC
    0.49
    Nee
    0.49
     Walkover
    0.48
    Activations Density 0.028%

    No Known Activations