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. 8101
    Prev
    Next
    INDEX
    Explanations

    specific scientific measurements and statistical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Initial letters that form the beginning of technical terms, brand names, acronyms, or specialized vocabulary in academic or technical contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    AISSEE
    -0.61
    IndentedString
    -0.55
     Herramientas
    -0.53
    хьтан
    -0.50
    Ingredienti
    -0.49
    InputTagHelper
    -0.49
     Komunikasi
    -0.49
     ilustração
    -0.47
     siquiera
    -0.46
     tématu
    -0.46
    POSITIVE LOGITS
     androidx
    0.40
    롭
    0.38
    ỏa
    0.37
     médié
    0.37
    apache
    0.37
     Eighteenth
    0.36
     hObject
    0.36
    prech
    0.35
     lantern
    0.35
    )|^{
    0.35
    Activations Density 0.607%

    No Known Activations