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. 7356
    Prev
    Next
    INDEX
    Explanations

    characteristics and properties of APIs or interfaces in software programming

    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
    ness
    -0.66
    škas
    -0.59
    çons
    -0.56
     metų
    -0.53
    nya
    -0.52
    ṅ
    -0.52
     stesse
    -0.52
     uova
    -0.51
    carbox
    -0.51
    ētu
    -0.49
    POSITIVE LOGITS
    i
    0.77
     Schi
    0.76
    iri
    0.76
    ini
    0.75
    ivi
    0.75
    ili
    0.75
    SSI
    0.74
    ti
    0.73
     Aki
    0.72
    Andi
    0.72
    Activations Density 0.391%

    No Known Activations