Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 216
    Prev
    Next
    INDEX
    Explanations

    terms related to vehicle recalls and associated issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to vehicle recalls and transmission problems, especially related to Volkswagen's DSG (Direct-Shift Gearbox) transmission.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jsii
    -0.38
     plataformas
    -0.33
    Préparation
    -0.31
    BeginContext
    -0.31
    platten
    -0.31
     aquarela
    -0.30
    AntiForgeryToken
    -0.30
    UnusedPrivate
    -0.29
     UnityEditor
    -0.29
     ModelExpression
    -0.29
    POSITIVE LOGITS
     unsafe
    0.58
     fubject
    0.54
     insuffisamment
    0.54
     NSCoder
    0.53
     recalled
    0.53
     Unsafe
    0.52
    unsafe
    0.51
     pelig
    0.51
     faſt
    0.51
     ""],
    0.50
    Activations Density 0.122%

    No Known Activations