© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2376
    Prev
    Next
    INDEX
    Explanations

    Japanese functional particles and sentence structure components

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

    Japanese and multilingual text segments, particularly grammatical particles and text from different languages.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     مشين
    -0.38
    issory
    -0.37
    OrEmpty
    -0.37
     lopp
    -0.35
    zegor
    -0.35
     ſta
    -0.33
     ſtate
    -0.32
     ruines
    -0.31
    わけではない
    -0.30
    bufio
    -0.29
    POSITIVE LOGITS
    esinde
    0.71
    하여
    0.67
    ेशा
    0.64
     yılında
    0.63
    되어
    0.63
    部は
    0.62
    HtmlAttribute
    0.62
    りで
    0.61
    으면
    0.61
    ில்
    0.61
    Activations Density 0.038%

    No Known Activations