© 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. 12-GEMMASCOPE-RES-16K
    6. 5602
    Prev
    Next
    INDEX
    Explanations

    sequences of whitespace or non-visible characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समीक्षाएं
    -0.58
    पया
    -0.50
     оригіналу
    -0.48
    chieht
    -0.47
    agisse
    -0.46
    principalColumn
    -0.46
     insuffisamment
    -0.46
     Grüße
    -0.45
     verheir
    -0.45
     humanidade
    -0.45
    POSITIVE LOGITS
      
    0.71
    ) 
    0.57
     (
    0.49
      
    0.47
    Ehr
    0.46
    NFC
    0.46
     Chinook
    0.46
    bile
    0.46
     ​​
    0.45
     Wunder
    0.45
    Activations Density 0.523%

    No Known Activations