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. 8232
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and data structures

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

    Code snippets or program names

    np_acts-logits-general · gemini-2.0-flash

    Tic Tac Toe, calculator, book, shop

    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
    WebElementEntity
    -0.38
    ิลปะ
    -0.31
    UnsafeEnabled
    -0.31
    dafx
    -0.31
    IBAction
    -0.30
    SourceChecksum
    -0.30
    krivning
    -0.29
    ルーム
    -0.29
     spieg
    -0.29
     tul
    -0.29
    POSITIVE LOGITS
     tartalomajánló
    0.68
    AndEndTag
    0.64
     Houſe
    0.54
    lifestyle
    0.52
     mAdapter
    0.52
    ༘
    0.51
    processable
    0.51
     houſe
    0.51
     $_(
    0.50
     '\\;'
    0.50
    Activations Density 0.090%

    No Known Activations