© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 105792
    Prev
    Next
    INDEX
    Explanations

    references to specific geographic locations or entities

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

    Word fragments that appear in specialized or technical terminology across various domains, including legal citations, scientific methods, programming terms, vehicle components, and mathematical concepts.

    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
     Wikiseite
    -0.68
     nonUne
    -0.59
     يتيمه
    -0.56
     lavable
    -0.51
    endpush
    -0.50
    transQ
    -0.49
    พาะ
    -0.47
     Gruber
    -0.47
     miniaturka
    -0.47
     ilustracja
    -0.46
    POSITIVE LOGITS
    FO
    0.47
     Palt
    0.46
    AddTagHelper
    0.46
    󠁮
    0.44
    lccccc
    0.43
     الميل
    0.43
    cogn
    0.42
    нъ
    0.42
    howe
    0.42
    ությ
    0.41
    Activations Density 0.227%

    No Known Activations