© 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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14050
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "command" and related terms within a programming context

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

    "command"

    np_acts-logits-general · gemini-2.0-flash

    command word

    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
     Hälfte
    -0.45
     Relaciones
    -0.41
    rotum
    -0.41
    lewati
    -0.38
     Vereinigte
    -0.36
    ̍
    -0.36
    Bissau
    -0.35
    Leslie
    -0.34
    issau
    -0.34
     rotina
    -0.33
    POSITIVE LOGITS
     Command
    1.35
     command
    1.34
     Commands
    1.24
     SqlCommand
    1.23
    Command
    1.21
     ICommand
    1.18
     commands
    1.17
    command
    1.16
     COMMAND
    1.16
    Commands
    1.09
    Activations Density 0.083%

    No Known Activations