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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8085
    Prev
    Next
    INDEX
    Explanations

    references to specific companies and their products in various industries

    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
    ftrag
    -0.43
    razio
    -0.40
     tea
    -0.37
     vectorielle
    -0.37
     redacción
    -0.35
     kahve
    -0.35
     uñas
    -0.35
     Trasp
    -0.35
     preuves
    -0.35
     fee
    -0.34
    POSITIVE LOGITS
     AssemblyVersion
    0.66
     manufacturer
    0.65
    sprodu
    0.64
     products
    0.63
     producers
    0.63
     Products
    0.63
     manufacturers
    0.61
     Producers
    0.61
     productions
    0.60
    manufact
    0.60
    Activations Density 0.023%

    No Known Activations