© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 3934
    Prev
    Next
    INDEX
    Explanations

    content related to reviewing and examining various types of materials and data

    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
    expandindo
    -0.73
    出版年
    -0.64
     utafitiHapana
    -0.63
    الحياه
    -0.63
     Wicidata
    -0.63
    MethodManager
    -0.62
     surla
    -0.62
     مشين
    -0.60
     transfieras
    -0.60
    hyrchwyd
    -0.60
    POSITIVE LOGITS
     carefully
    1.88
     closely
    1.83
     Carefully
    1.38
    caref
    1.34
     внимательно
    1.30
     careful
    1.30
     attentively
    1.28
     cuidadosamente
    1.22
     intently
    1.20
     Careful
    1.06
    Activations Density 0.458%

    No Known Activations