© 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. 39-GEMMASCOPE-RES-16K
    6. 1827
    Prev
    Next
    INDEX
    Explanations

    technical terminology and keywords related to coding and programming concepts

    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
     towards
    -0.49
     with
    -0.48
     toward
    -0.46
     vnder
    -0.45
    towards
    -0.45
     until
    -0.44
    within
    -0.44
     within
    -0.43
     without
    -0.43
    toward
    -0.42
    POSITIVE LOGITS
     Infór
    0.77
     humanidade
    0.77
     Inscrivez
    0.70
     coroa
    0.69
     maternidade
    0.68
     paisagem
    0.65
     liderança
    0.64
     increí
    0.62
     amizade
    0.61
     veckor
    0.60
    Activations Density 0.121%

    No Known Activations