© 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. 41994
    Prev
    Next
    INDEX
    Explanations

    symbols or operators related to programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    RenderAtEndOf
    -0.61
    verwijspagina
    -0.60
    cifix
    -0.54
    modelBuilder
    -0.52
    webElementXpaths
    -0.50
     utafitiHapana
    -0.50
    riors
    -0.48
    NewRow
    -0.46
    }));
    
    -0.45
     
    -0.44
    POSITIVE LOGITS
     Offset
    0.91
     offset
    0.71
     offsets
    0.69
    Offset
    0.69
    offset
    0.63
     OFFSET
    0.51
    Offsets
    0.51
    偏移
    0.49
    offsets
    0.48
    GraphicsUnit
    0.43
    Activations Density 0.001%

    No Known Activations