© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 82221
    Prev
    Next
    INDEX
    Explanations

    formatting details related to dimensions and layout in design specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    units like px, pt, dp, mu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.86
    GraphicsUnit
    -0.72
     tartalomajánló
    -0.66
     MainAxisSize
    -0.66
    ロウィン
    -0.63
    enablog
    -0.63
    rungsseite
    -0.62
     nahilalakip
    -0.60
     pinulongan
    -0.60
     kasarigan
    -0.59
    POSITIVE LOGITS
    CodedInputStream
    0.41
                           
    0.33
                                   
    0.30
                            
    0.30
                 
    0.29
    During
    0.28
                          
    0.28
    esterno
    0.28
     During
    0.28
    Left
    0.28
    Activations Density 0.009%

    No Known Activations