© 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. 40-GEMMASCOPE-RES-16K
    6. 1974
    Prev
    Next
    INDEX
    Explanations

    code syntax structures indicating conditional logic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    蚪
    -0.43
     وتسجيلات
    -0.43
     "");
    
    -0.42
    henswürdigkeiten
    -0.42
    ]&
    -0.40
    MessageTagHelper
    -0.40
    athione
    -0.40
     */
    
    
    -0.39
     '
    
    -0.39
     AssemblyTitle
    -0.39
    POSITIVE LOGITS
     return
    0.87
    return
    0.74
     continue
    0.69
    continue
    0.60
     then
    0.60
     break
    0.57
     thì
    0.54
    then
    0.54
    break
    0.52
    ||
    0.51
    Activations Density 0.131%

    No Known Activations