© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16285
    Prev
    Next
    INDEX
    Explanations

    structured initialization markers or delimiters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     Италијани
    -0.45
    蚪
    -0.38
    ArgumentParser
    -0.38
     otomatig
    -0.38
    洋
    -0.36
    請繼續往下閱讀
    -0.36
    źć
    -0.36
    FDRE
    -0.36
    AutoresizingMask
    -0.35
    百万
    -0.35
    POSITIVE LOGITS
    TagMode
    0.54
    MemoryWarning
    0.53
    +#+
    0.50
     समीक्षाओं
    0.46
     esclavos
    0.45
    Бахар
    0.45
     محفوظة
    0.45
     yelek
    0.44
     FontWeight
    0.44
    inWeight
    0.44
    Activations Density 0.069%

    No Known Activations