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. 1543
    Prev
    Next
    INDEX
    Explanations

    questions related to comparisons and mathematical evaluations

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

    Starts with "Is", "Does", "Which", or "What"

    np_acts-logits-general · gemini-2.0-flash

    questions about numbers

    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
    setVerticalGroup
    -1.10
     queſta
    -0.97
    adaptiveStyles
    -0.96
     betweenstory
    -0.93
     незавершена
    -0.92
     Мексичка
    -0.90
    Autoritní
    -0.88
     NSCoder
    -0.88
    windowFixed
    -0.88
    ArrowToggle
    -0.87
    POSITIVE LOGITS
     
    0.40
    ’
    0.34
    '
    0.31
     the
    0.31
     "
    0.31
     behind
    0.30
     Hal
    0.29
    mathrm
    0.28
     m
    0.28
     early
    0.28
    Activations Density 0.448%

    No Known Activations