© 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. 409
    Prev
    Next
    INDEX
    Explanations

    references to documentation and API structures related to a specific programming framework or library

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

    URLs or web API elements

    np_acts-logits-general · gemini-2.0-flash

    web api sales orders

    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
     chi̍t
    -0.45
    rrggbb
    -0.38
     Vikipedi
    -0.36
     للاسماء
    -0.34
    Sainte
    -0.34
    deelte
    -0.33
    Tembelea
    -0.32
    提
    -0.32
    archiviato
    -0.31
     Tun
    -0.31
    POSITIVE LOGITS
    Portale
    0.75
    ftagPool
    0.63
    Portail
    0.63
    
    0.61
     Autorizaciones
    0.60
    TagMode
    0.59
     kaarangay
    0.58
     @"/
    0.58
    ::_('
    0.55
     "..\..\..\
    0.52
    Activations Density 0.597%

    No Known Activations