© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 4275
    Prev
    Next
    INDEX
    Explanations

    terms related to networking protocols or configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     delincuentes
    -0.51
     cantantes
    -0.48
     jueces
    -0.46
     cómics
    -0.44
     tatuajes
    -0.44
     espírit
    -0.43
     inmigrantes
    -0.43
     residentes
    -0.43
     alrededores
    -0.43
     minerales
    -0.42
    POSITIVE LOGITS
    tos
    1.71
    inos
    1.59
    nos
    1.59
    anos
    1.55
    ios
    1.54
    vos
    1.52
    gos
    1.52
    atos
    1.49
    mos
    1.44
    dos
    1.43
    Activations Density 0.298%

    No Known Activations