© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10322
    Prev
    Next
    INDEX
    Explanations

    references to statistical data or percentages related to health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     ProtoMessage
    -0.62
    prefixer
    -0.61
     surla
    -0.61
    adaptiveStyles
    -0.57
     ivelany
    -0.57
     disambiguazione
    -0.57
    WriteTagHelper
    -0.56
    
    -0.56
    Panamoan
    -0.56
    MemoryWarning
    -0.56
    POSITIVE LOGITS
     XNUMX
    0.41
     judgment
    0.38
     analyzes
    0.35
     honor
    0.35
     behavior
    0.35
    ization
    0.35
    ChildScrollView
    0.34
     esclavos
    0.33
     calculation
    0.33
    NUMX
    0.33
    Activations Density 1.212%

    No Known Activations