© 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. 39-GEMMASCOPE-RES-16K
    11. 3643
    Prev
    Next
    INDEX
    Explanations

    queries and requests related to information and guidance in problem-solving contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.46
    MCE
    -0.29
    sieger
    -0.28
     essentially
    -0.25
     actually
    -0.25
     feuille
    -0.25
     basically
    -0.24
    基本
    -0.23
    AutoScaleMode
    -0.23
     indeed
    -0.23
    POSITIVE LOGITS
    parsedMessage
    0.82
     surla
    0.81
     '\\;'
    0.76
     able
    0.71
     aware
    0.66
    Източници
    0.65
    ніципалі
    0.64
     AssemblyTitle
    0.64
     fulfilled
    0.63
     satisfied
    0.61
    Activations Density 0.690%

    No Known Activations