Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73722
    Prev
    Next
    INDEX
    Explanations

    structural elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     desmotivaciones
    -0.54
    pulseira
    -0.52
     mempel
    -0.50
    pingente
    -0.50
     votación
    -0.48
     Segurança
    -0.47
     aleación
    -0.47
    brinco
    -0.47
     SDLK
    -0.46
     disfraces
    -0.46
    POSITIVE LOGITS
    SequentialGroup
    0.65
    SourceChecksum
    0.60
    Искәрмәләр
    0.54
    complexContent
    0.49
     referenties
    0.45
    GOTREF
    0.44
     BoxDecoration
    0.42
     autorytatywna
    0.41
    Composable
    0.41
    enterOuterAlt
    0.40
    Activations Density 0.001%

    No Known Activations