© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 10333
    Prev
    Next
    INDEX
    Explanations

    instances of the word "show" and its variations in requests or commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.50
    ViewFeatures
    -0.34
     Tode
    -0.32
    Anlage
    -0.32
    ीय
    -0.31
    er
    -0.31
    oneta
    -0.31
     seeing
    -0.31
    >>>
    -0.30
    internalType
    -0.30
    POSITIVE LOGITS
    casing
    0.89
    stopper
    0.82
    cased
    0.81
    rooms
    0.75
    manship
    0.74
    CASE
    0.66
    reel
    0.66
    downs
    0.64
    piece
    0.61
    cases
    0.59
    Activations Density 0.185%

    No Known Activations