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. 14678
    Prev
    Next
    INDEX
    Explanations

    user interface (UI) elements and layout specifications in code snippets

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

    Code, styling, or user interface elements

    np_acts-logits-general · gemini-2.0-flash

    CSS pseudo-selectors and styling

    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
    ThroughAttribute
    -0.59
    ########.
    -0.48
    TagMode
    -0.44
    providedIn
    -0.44
     tartalomajánló
    -0.44
     utafitiHapana
    -0.44
    ibouti
    -0.43
    ImageContext
    -0.42
    #
    -0.41
     виправивши
    -0.40
    POSITIVE LOGITS
     makeStyles
    0.90
     useStyles
    0.70
     ſta
    0.60
    InputLabel
    0.57
     pleaſure
    0.56
    AnimationsModule
    0.55
    Toledo
    0.54
    mui
    0.52
    SizeF
    0.51
     BorderSide
    0.50
    Activations Density 0.017%

    No Known Activations