© 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. 12256
    Prev
    Next
    INDEX
    Explanations

    references to health metrics and standards, particularly those associated with acceptable values for various tests and indices

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

    Acceptable or normal limits/thresholds

    np_acts-logits-general · gemini-2.0-flash

    defining thresholds and limits

    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
     protoimpl
    -0.47
     '{@
    -0.35
     habet
    -0.33
    "}")
    -0.32
    extAlignment
    -0.30
    Executed
    -0.30
     BLOCK
    -0.29
    expose
    -0.29
     peel
    -0.29
     туры
    -0.28
    POSITIVE LOGITS
     thresholds
    0.66
     criteria
    0.64
     threshold
    0.63
    EDEFAULT
    0.61
     critères
    0.60
     standards
    0.58
     Criteria
    0.58
    reshold
    0.57
     ideal
    0.57
     Empfehlung
    0.56
    Activations Density 0.880%

    No Known Activations