© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 8953
    Prev
    Next
    INDEX
    Explanations

    references to specific types of media or digital content

    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
     -
    -0.51
    ↵
    -0.50
     •
    -0.50
     --
    -0.47
     //
    -0.47
     Various
    -0.43
     the
    -0.42
     —
    -0.41
     is
    -0.41
    ----------------
    -0.41
    POSITIVE LOGITS
    routeProvider
    0.57
     мәкал
    0.57
    modus
    0.57
    bona
    0.55
     noqa
    0.55
    OleDb
    0.54
     iprot
    0.54
    :✨
    0.54
     BoxFit
    0.52
    sine
    0.52
    Activations Density 0.256%

    No Known Activations