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

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15069
    Prev
    Next
    INDEX
    Explanations

    structured formats and organizational elements in text, such as meeting details or headers

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

    Legal case citations and dates

    np_acts-logits-general · gemini-2.0-flash

    court and legal case information

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    جوايز
    -0.36
     circular
    -0.36
     earlier
    -0.35
     nhất
    -0.35
     arm
    -0.34
     logic
    -0.33
     comps
    -0.33
     dated
    -0.33
    fontWeight
    -0.33
     Twice
    -0.33
    POSITIVE LOGITS
    exitRule
    0.65
    
    0.64
    kháu
    0.63
    AccessorTable
    0.62
    parsedMessage
    0.56
    FieldBuilder
    0.55
     ExecuteAsync
    0.54
    SizeF
    0.54
    PrototypeOf
    0.53
    errHandler
    0.53
    Activations Density 0.592%

    No Known Activations