© 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. 41-GEMMASCOPE-RES-16K
    6. 10301
    Prev
    Next
    INDEX
    Explanations

    references to physical tasks and processes related to both human and mechanical systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Дереккөздер
    -0.52
    verifyException
    -0.48
    GEBURTSDATUM
    -0.44
     createSlice
    -0.36
    Попис
    -0.35
    WillAppear
    -0.35
    viana
    -0.35
     reunion
    -0.35
    queros
    -0.34
    ValueStyle
    -0.34
    POSITIVE LOGITS
     perform
    2.08
     performing
    2.03
     performs
    1.93
     Perform
    1.86
    Perform
    1.80
    Performing
    1.78
     Performing
    1.75
     conducting
    1.72
     conduct
    1.69
     performed
    1.67
    Activations Density 0.871%

    No Known Activations