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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 13329
    Prev
    Next
    INDEX
    Explanations

    elements of code related to audio processing and management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ...</
    -0.30
    AddAttribute
    -0.29
    HasAnnotation
    -0.29
    مقاله
    -0.28
     dîner
    -0.28
    олові
    -0.28
     Caballero
    -0.28
    {})
    -0.27
    genesis
    -0.27
    plish
    -0.27
    POSITIVE LOGITS
    httphttps
    0.67
    ագրություններ
    0.67
    rungsseite
    0.66
    Hentet
    0.62
    SpringBootTest
    0.61
    RenderAtEndOf
    0.60
    contentLoaded
    0.59
    migrationBuilder
    0.56
    MessageWindow
    0.55
    :✨
    0.54
    Activations Density 0.441%

    No Known Activations