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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2860
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting and mathematical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     terciopelo
    -0.37
     quizá
    -0.33
     nocturno
    -0.33
     adopción
    -0.33
     supervivencia
    -0.33
     experiencia
    -0.32
     bañera
    -0.32
     compañ
    -0.31
     entretenimiento
    -0.30
     aunque
    -0.30
    POSITIVE LOGITS
     المعيارى
    0.79
    IUrlHelper
    0.79
    expandindo
    0.79
     defaultstate
    0.77
    Personensuche
    0.73
     ExecuteAsync
    0.73
    migrationBuilder
    0.72
    transQ
    0.71
    verwijspagina
    0.69
     שוליים
    0.68
    Activations Density 1.103%

    No Known Activations