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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 15192
    Prev
    Next
    INDEX
    Explanations

    terms related to virtualization and containerization technology

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

    virtualization software

    np_acts-logits-general · gemini-2.0-flash

    Docker, virtual machines, wine

    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
    komsten
    -0.44
    Посилання
    -0.43
     agradec
    -0.43
    brunn
    -0.42
    ien
    -0.41
    estimm
    -0.40
    sen
    -0.40
     Fras
    -0.40
    komst
    -0.39
    +#+
    -0.39
    POSITIVE LOGITS
     فريبيس
    0.50
    SBATCH
    0.50
    TagMode
    0.49
    estacks
    0.48
    migrationBuilder
    0.45
    الحياه
    0.43
     Docker
    0.42
    isolation
    0.41
     CanadaChoose
    0.41
    setViewportView
    0.39
    Activations Density 0.466%

    No Known Activations