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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5210
    Prev
    Next
    INDEX
    Explanations

    phrases related to electrical and mechanical performance issues in motors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :]:
    -0.35
    dorff
    -0.34
     eraser
    -0.33
    lapi
    -0.33
     barrier
    -0.33
    fastjson
    -0.32
    ValueStyle
    -0.32
     friends
    -0.32
    ]")]
    -0.32
     post
    -0.32
    POSITIVE LOGITS
     output
    0.64
     PERFORMANCE
    0.60
    Performance
    0.59
    Leistung
    0.59
     Leistungs
    0.59
     출력
    0.59
     Output
    0.57
     Performance
    0.57
     Leistung
    0.55
     performance
    0.54
    Activations Density 0.746%

    No Known Activations