© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1250
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditions, results, or discussions about measurement and limits

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

    Followed by numbers or math symbols

    np_acts-logits-general · gemini-2.0-flash

    firstly, Appendix, much

    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
    ThroughAttribute
    -0.53
    Personensuche
    -0.47
     alimentaires
    -0.40
     ApiException
    -0.40
    berdayakan
    -0.39
    ImageContext
    -0.39
     boneca
    -0.39
     resourceCulture
    -0.39
     Superan
    -0.38
     urodz
    -0.38
    POSITIVE LOGITS
    SequentialGroup
    0.53
    BagConstraints
    0.52
    enciaga
    0.50
     priority
    0.47
     concept
    0.47
    kswagen
    0.45
    frames
    0.44
     points
    0.44
     implementation
    0.44
     erkennen
    0.43
    Activations Density 1.276%

    No Known Activations