© 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. 41-GEMMASCOPE-RES-16K
    11. 7138
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to automotive and mechanical technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eerder
    -0.62
    httphttps
    -0.60
    çade
    -0.58
    MigrationBuilder
    -0.56
    zzleHttp
    -0.56
    -------------</
    -0.54
     propOrder
    -0.54
     gesteld
    -0.54
     nooit
    -0.53
     wiedzieć
    -0.53
    POSITIVE LOGITS
    sty
    0.40
    ny
    0.40
    mål
    0.40
    forhold
    0.38
    fär
    0.38
    förs
    0.38
    stø
    0.38
    över
    0.37
    ljiv
    0.37
    före
    0.37
    Activations Density 0.025%

    No Known Activations