Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 45902
    Prev
    Next
    INDEX
    Explanations

    mentions of the Linux operating system

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

    Linux operating system

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     predeceased
    -0.46
    thenReturn
    -0.44
     day
    -0.43
    ValueStyle
    -0.42
    Đi
    -0.40
     Coyle
    -0.40
     of
    -0.40
     Goal
    -0.39
    McC
    -0.39
     consultato
    -0.39
    POSITIVE LOGITS
     Linux
    1.30
    Linux
    1.22
     linux
    1.16
    linux
    1.12
    LINUX
    0.91
     Unix
    0.84
    Unix
    0.84
     unix
    0.83
     UNIX
    0.82
    UNIX
    0.78
    Activations Density 0.008%

    No Known Activations