© 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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8967
    Prev
    Next
    INDEX
    Explanations

    elements related to website features and updates

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

    Visual design and user interface

    np_acts-logits-general · gemini-2.0-flash

    visual design and user experience

    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
    LElement
    -0.50
     HasFactory
    -0.45
    andExpect
    -0.45
     cardíaca
    -0.41
    ühungen
    -0.40
    principalTable
    -0.38
     通販
    -0.38
    UnsafeEnabled
    -0.38
    apimachinery
    -0.38
     Wartawan
    -0.37
    POSITIVE LOGITS
     design
    0.52
     storytelling
    0.52
     graphics
    0.52
     fidget
    0.51
     creative
    0.50
     creatives
    0.50
     graphic
    0.49
     designer
    0.49
     banner
    0.49
    ceros
    0.48
    Activations Density 0.228%

    No Known Activations