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. 3585
    Prev
    Next
    INDEX
    Explanations

    specifications and parameters related to dimensions or sizes in code

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

    Tokens indicating size, especially "width" or "diameter"

    np_acts-logits-general · gemini-2.0-flash

    width and dimensions

    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
    exitRule
    -0.55
    __(/*!
    -0.53
    脚注の使い方
    -0.51
    Билгалдахарш
    -0.51
    webElementXpaths
    -0.49
    UnsafeEnabled
    -0.48
     Cay
    -0.47
    +#+#
    -0.47
     CGPoint
    -0.47
    +:+
    -0.47
    POSITIVE LOGITS
     Width
    1.35
     width
    1.34
    Width
    1.32
    width
    1.30
    WIDTH
    1.10
     widths
    1.05
     WIDTH
    0.98
     getWidth
    0.96
    setWidth
    0.95
    getWidth
    0.94
    Activations Density 0.084%

    No Known Activations