© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9850
    Prev
    Next
    INDEX
    Explanations

    references to sections or components in a structured report or document, denoting specific parts of a case or study

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

    Likely citations, references, or IDs

    np_acts-logits-general · gemini-2.0-flash

    numerical sequences with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     veuillez
    -0.33
    idł
    -0.29
    ٌ
    -0.28
    RectF
    -0.27
     эпи
    -0.27
     الو
    -0.26
    ganggu
    -0.26
     et
    -0.26
     Monday
    -0.25
    __':
    
    -0.25
    POSITIVE LOGITS
     propOrder
    0.81
    RTEE
    0.75
     sessionFactory
    0.64
    parsedMessage
    0.63
    хьтан
    0.62
     Италијани
    0.62
    majánló
    0.62
    PhysRevLett
    0.61
    ロウィン
    0.61
    exitRule
    0.60
    Activations Density 1.193%

    No Known Activations