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. 31-GEMMASCOPE-RES-16K
    6. 9388
    Prev
    Next
    INDEX
    Explanations

    elements of code and programming structures

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

    file paths and directory structures in code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.38
     apport
    -0.34
    SuccessListener
    -0.34
     rechange
    -0.33
    setScene
    -0.32
    мә
    -0.32
     setError
    -0.32
     imprimible
    -0.31
     Kearns
    -0.31
     verba
    -0.31
    POSITIVE LOGITS
     Featured
    0.90
     featured
    0.84
     trending
    0.84
    Featured
    0.83
     Trending
    0.82
     carousel
    0.79
     banner
    0.78
     Banner
    0.75
    featured
    0.75
     Recommended
    0.74
    Activations Density 0.263%

    No Known Activations