© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 58122
    Prev
    Next
    INDEX
    Explanations

    references to language and the concept of words

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

    spoken or written words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    ilaire
    -0.42
    有一個
    -0.39
     захворю
    -0.38
    essoal
    -0.37
    umably
    -0.36
     hangout
    -0.36
     upkeep
    -0.35
     אף
    -0.35
     beraber
    -0.35
     presumably
    -0.35
    POSITIVE LOGITS
     words
    1.16
    Words
    1.13
     WORDS
    1.09
     Words
    1.06
    words
    0.96
    WORDS
    0.88
     Worte
    0.87
    avras
    0.84
     palabras
    0.81
     слова
    0.79
    Activations Density 0.013%

    No Known Activations