© 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
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14969
    Prev
    Next
    INDEX
    Explanations

    function definitions and API-related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     even
    -0.35
     encant
    -0.35
     cenar
    -0.35
    Gön
    -0.34
     choć
    -0.32
     only
    -0.32
     selamat
    -0.31
     Incluso
    -0.31
     вовсе
    -0.31
     ánimo
    -0.31
    POSITIVE LOGITS
    تقاوى
    0.63
     препратки
    0.62
    Rüyada
    0.61
    SourceChecksum
    0.59
    Бахар
    0.58
    HasAnnotation
    0.58
     ErrIntOverflow
    0.56
     Meksiku
    0.55
     EnglishChoose
    0.53
    يكب
    0.53
    Activations Density 0.991%

    No Known Activations