© 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. 50481
    Prev
    Next
    INDEX
    Explanations

    references to API functions and data handling processes

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

    API and web service calls

    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
     AssemblyCulture
    -0.40
    CloseOperation
    -0.31
    CppMethod
    -0.29
    HasAnnotation
    -0.28
     deficits
    -0.27
    Děkuji
    -0.26
    Obrázky
    -0.26
     Verlet
    -0.26
    ocry
    -0.26
     disbelief
    -0.25
    POSITIVE LOGITS
    EndGlobalSection
    0.74
    pushFollow
    0.70
     nonUne
    0.62
     smtplib
    0.59
    脚注の使い方
    0.55
     <>",
    0.53
    awaiter
    0.53
    Pranala
    0.52
    interopRequire
    0.51
    MigrationBuilder
    0.51
    Activations Density 0.039%

    No Known Activations