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-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 10249
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to programming, particularly in the context of code execution, updates, and error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.59
    ltä
    -0.52
     ویکی‌پدی
    -0.51
    culously
    -0.51
     initComponents
    -0.50
    ergic
    -0.47
     úteis
    -0.47
    principalColumn
    -0.47
     חיצוניים
    -0.47
     $_(
    -0.47
    POSITIVE LOGITS
     incen
    0.40
     Sensation
    0.40
     mechanism
    0.40
    PropertyChanging
    0.39
    HINT
    0.39
    ration
    0.38
     ration
    0.38
     Aid
    0.38
    estion
    0.38
     aid
    0.37
    Activations Density 0.841%

    No Known Activations