© 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. 13647
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to solving chess compositions and problems

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

    Follows quantities or percentages

    np_acts-logits-general · gemini-2.0-flash

    words, numbers, and non-English characters

    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
    KommentareTeilen
    -0.40
     fubject
    -0.39
     purpoſe
    -0.38
     houſe
    -0.36
    Etimología
    -0.33
     fhort
    -0.32
     poffible
    -0.31
     raza
    -0.31
     viſ
    -0.31
     ſmall
    -0.30
    POSITIVE LOGITS
     ویکی‌پدی
    0.72
     autorytatywna
    0.70
    expandindo
    0.63
    MigrationBuilder
    0.60
    NameInMap
    0.58
    Jeografia
    0.54
    DoubleQuotes
    0.53
     ujednoznacz
    0.52
     Chwiliwch
    0.52
    ************
    0.51
    Activations Density 1.032%

    No Known Activations