© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14241
    Prev
    Next
    INDEX
    Explanations

    text related to player performance and statistics in sports

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

    followed by apostrophe and a single character

    np_acts-logits-general · gemini-2.0-flash

    numbers in dates or quantities

    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
    पया
    -0.49
     оригіналу
    -0.42
    contentLoaded
    -0.41
    ută
    -0.37
     Мексичка
    -0.37
    istoitu
    -0.36
     golpea
    -0.36
     scattata
    -0.35
     rând
    -0.35
    koľ
    -0.34
    POSITIVE LOGITS
     utafitiHapana
    0.52
    UpInside
    0.44
    bootstrapcdn
    0.43
    FormTagHelper
    0.43
    setAuto
    0.42
    Slf
    0.41
    UnusedPrivate
    0.41
    UseVisualStyle
    0.40
    <?,
    0.40
    expandindo
    0.40
    Activations Density 1.319%

    No Known Activations