Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12443
    Prev
    Next
    INDEX
    Explanations

    code-related structures, specifically focusing on method definitions and return statements

    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
    الحياه
    -0.65
     الدولى
    -0.64
     ddelweddau
    -0.61
     للمعارف
    -0.60
    qvarna
    -0.58
     архивлан
    -0.58
    einander
    -0.53
     상세
    -0.53
    PreferredItem
    -0.52
    hoeddwyd
    -0.48
    POSITIVE LOGITS
    findpost
    0.59
     désolés
    0.56
    __":
    
    0.55
    parsedMessage
    0.53
     INTERPRET
    0.51
    InputBorder
    0.50
    脚注の使い方
    0.50
    addCriterion
    0.49
     removeFrom
    0.49
     Anz
    0.47
    Activations Density 0.028%

    No Known Activations