© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11506
    Prev
    Next
    INDEX
    Explanations

    references to specific names, particularly individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     obvious
    -0.44
    TintMode
    -0.40
     orange
    -0.40
    Karakteristik
    -0.39
     optar
    -0.38
    marshaller
    -0.37
    JpaRepository
    -0.37
     Highly
    -0.37
     mey
    -0.36
     optical
    -0.36
    POSITIVE LOGITS
     saites
    0.61
    hoeddwyd
    0.57
    lahoma
    0.48
    outSlope
    0.47
    rungsseite
    0.47
    __((
    0.47
    Посилання
    0.47
     للاسماء
    0.46
    enumi
    0.46
    Hochspringen
    0.46
    Activations Density 1.214%

    No Known Activations