© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 4078
    Prev
    Next
    INDEX
    Explanations

    programming concepts and keywords related to function definitions and property manipulation in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    -0.63
    __":
    -0.63
    __":
    
    -0.59
     nakalista
    -0.57
     Meksiku
    -0.52
    __':
    
    -0.52
    хьтан
    -0.52
    modb
    -0.50
     Headaches
    -0.50
    ulongan
    -0.50
    POSITIVE LOGITS
    Or
    0.71
    To
    0.65
    At
    0.65
    Of
    0.65
    By
    0.64
    And
    0.64
    On
    0.61
    For
    0.61
    Per
    0.60
    Re
    0.60
    Activations Density 1.235%

    No Known Activations