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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 72827
    Prev
    Next
    INDEX
    Explanations

    programming code structures and numeric references

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

    code, variables, and punctuation

    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
     interp
    -0.51
    ConstraintMaker
    -0.50
     ſind
    -0.48
    oprot
    -0.48
     pleaſure
    -0.47
     $_"
    -0.45
     templ
    -0.45
     queſta
    -0.45
     ché
    -0.45
     autom
    -0.44
    POSITIVE LOGITS
     propOrder
    0.66
    Життєпис
    0.51
    InstrumentedTest
    0.45
     ويكيميديا
    0.43
    曖昧さ回避
    0.43
     discapacidad
    0.42
     manicura
    0.39
    Véxase
    0.38
    hyrchwyd
    0.38
     gustaba
    0.38
    Activations Density 0.007%

    No Known Activations