© 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. 55122
    Prev
    Next
    INDEX
    Explanations

    technical elements related to function definitions and parameter handling in programming

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

    technical terms and languages

    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
     ujednoznacz
    -0.86
     Autorizaciones
    -0.84
     disambiguazione
    -0.79
     ویکی‌پدی
    -0.79
     Menſchen
    -0.69
    iſchen
    -0.69
     erſten
    -0.69
    <unused16>
    -0.68
    <unused3>
    -0.67
    <unused47>
    -0.67
    POSITIVE LOGITS
    kuuta
    0.32
     degré
    0.31
     jäl
    0.27
    ml
    0.27
     itse
    0.26
     seed
    0.26
     level
    0.25
     langage
    0.25
     itself
    0.25
     רח
    0.25
    Activations Density 0.083%

    No Known Activations