© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3632
    Prev
    Next
    INDEX
    Explanations

    significant data entries or identifiers from a programming or technical context

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

    Hexadecimal strings

    np_acts-logits-general · gemini-2.0-flash

    hex identifiers or codes

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    uxxxx
    -0.35
     provincias
    -0.34
     colecciones
    -0.34
     Camilo
    -0.32
    Precalculus
    -0.32
    emballage
    -0.32
     ancestor
    -0.32
     poches
    -0.31
    gerichte
    -0.31
    DoubleQuotes
    -0.30
    POSITIVE LOGITS
    ItemBackground
    0.61
    хьтан
    0.58
    (!__
    0.57
    Personendaten
    0.57
    TypedDataSet
    0.55
    
    0.54
    yntaxException
    0.54
     poffible
    0.52
    
    0.52
    Chham
    0.51
    Activations Density 0.104%

    No Known Activations