© 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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 4386
    Prev
    Next
    INDEX
    Explanations

    mechanical and maintenance-related details of a vehicle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     réfrig
    -0.60
     particulières
    -0.58
     portátiles
    -0.55
     bijzondere
    -0.53
     ufficio
    -0.52
    dike
    -0.51
     sicura
    -0.51
    pixabay
    -0.51
    endaftaran
    -0.49
     colchón
    -0.49
    POSITIVE LOGITS
     aftermarket
    1.07
     custom
    0.84
     Custom
    0.83
    Custom
    0.77
     kit
    0.76
     autorytatywna
    0.76
     upgrade
    0.76
    custom
    0.72
     upgrades
    0.72
     CURIAM
    0.71
    Activations Density 0.154%

    No Known Activations