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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 42338
    Prev
    Next
    INDEX
    Explanations

    features and aesthetics of computer hardware components

    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
     Tup
    -0.41
    nest
    -0.40
     sol
    -0.39
     conc
    -0.39
    Tup
    -0.38
     Dots
    -0.38
    UTF
    -0.38
     transcript
    -0.37
     fores
    -0.37
    Fld
    -0.37
    POSITIVE LOGITS
     surla
    0.57
    tinyos
    0.57
    GEBURTSDATUM
    0.51
     ventilación
    0.49
     Ambiental
    0.48
     lenker
    0.48
    Personensuche
    0.48
    fortawesome
    0.48
    awtextra
    0.47
     Offisielt
    0.47
    Activations Density 0.006%

    No Known Activations