© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 4217
    Prev
    Next
    INDEX
    Explanations

    XML parameters and statistics related to memory and processing performance

    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
    parsedMessage
    -1.23
    <unused8>
    -1.07
    <unused23>
    -1.07
    <unused43>
    -1.07
    <unused51>
    -1.07
    [@BOS@]
    -1.07
    <unused16>
    -1.07
    <unused42>
    -1.07
    <unused74>
    -1.07
    <unused41>
    -1.07
    POSITIVE LOGITS
     city
    0.37
    ↵↵
    0.33
     book
    0.32
    ↵
    0.31
     
    0.31
      
    0.30
     food
    0.30
     girl
    0.28
    ,
    0.28
    <eos>
    0.28
    Activations Density 0.536%

    No Known Activations