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

    Neuronpedia

    Jacobian LensNEW
    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. 31-GEMMASCOPE-RES-16K
    11. 5493
    Prev
    Next
    INDEX
    Explanations

    elements related to articles, documents, and content availability

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

    statements indicating a document or content is available only to registered users or has access restrictions.

    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
     say
    -0.46
    SourceChecksum
    -0.41
     attribute
    -0.40
     alluded
    -0.39
    ữ
    -0.37
    say
    -0.37
     this
    -0.37
     banner
    -0.36
     tavola
    -0.35
     merito
    -0.34
    POSITIVE LOGITS
    TypedDataSet
    0.64
     defaultstate
    0.62
    IsContent
    0.56
    reportWebVitals
    0.55
    ChildScrollView
    0.55
    存于互联网档案馆
    0.55
    httphttps
    0.55
    __*/
    0.54
    DockStyle
    0.54
    XmlAccessType
    0.52
    Activations Density 0.331%

    No Known Activations