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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15137
    Prev
    Next
    INDEX
    Explanations

    elements related to API request and response 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
    UnusedPrivate
    -0.60
     deletes
    -0.59
    
    -0.57
     BorderLayout
    -0.56
     للاسماء
    -0.54
     invokingState
    -0.53
     reinstalling
    -0.53
     StringTokenizer
    -0.53
    BagConstraints
    -0.53
     deleting
    -0.53
    POSITIVE LOGITS
     perform
    0.85
     execute
    0.79
    execute
    0.72
     run
    0.69
    perform
    0.67
     Perform
    0.66
    invoke
    0.66
     invoke
    0.63
     do
    0.60
    run
    0.59
    Activations Density 0.539%

    No Known Activations