© 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. 22-GEMMASCOPE-RES-16K
    6. 5913
    Prev
    Next
    INDEX
    Explanations

    instances of formatting or structural changes in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.54
     BoxDecoration
    -0.52
     truy
    -0.50
    GraphicsUnit
    -0.49
    पया
    -0.48
     Descubre
    -0.46
    reiten
    -0.45
    ruptedException
    -0.43
     insuffisamment
    -0.43
    AnchorStyles
    -0.42
    POSITIVE LOGITS
    
    0.57
      
    0.51
    ########.
    0.51
     désolés
    0.50
    Aaa
    0.50
     defStyleAttr
    0.49
     __
    
    0.49
    «<
    0.47
     ProtoMessage
    0.47
    Baum
    0.47
    Activations Density 0.676%

    No Known Activations