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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8586
    Prev
    Next
    INDEX
    Explanations

    HTML elements related to navigation and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    BagLayout
    -0.37
    cvtColor
    -0.36
     &___
    -0.36
    Бахар
    -0.35
    protoimpl
    -0.35
     continúas
    -0.34
     cmap
    -0.33
     increíbles
    -0.33
     WILL
    -0.32
    ništ
    -0.32
    POSITIVE LOGITS
    ReusableCell
    0.75
    WidgetItem
    0.72
    IBarButtonItem
    0.63
     BorderSide
    0.63
    UIControlState
    0.63
    ⟬
    0.62
    PCell
    0.62
    Rohy
    0.59
     ListItem
    0.57
    ElementException
    0.56
    Activations Density 0.049%

    No Known Activations