© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 108559
    Prev
    Next
    INDEX
    Explanations

    code blocks and structural syntax elements, such as braces and parentheses, typically used in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    PYX
    -0.48
    IMPORTED
    -0.44
    ern
    -0.43
    ین
    -0.42
    glVertex
    -0.40
    tern
    -0.40
    ERN
    -0.40
     eam
    -0.40
     Eastern
    -0.40
    PhysRev
    -0.40
    POSITIVE LOGITS
     disambiguazione
    0.72
    __":
    0.71
    :^{
    0.69
     {
    0.69
    __":
    0.69
     producenta
    0.66
    
    0.66
    __':
    0.65
    Geografía
    0.64
     Bewußt
    0.63
    Activations Density 0.194%

    No Known Activations