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

    Neuronpedia

    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. 6080
    Prev
    Next
    INDEX
    Explanations

    notable individuals and their affiliations or educational backgrounds

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

    headings and section labels that introduce lists of notable people or items.

    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
    IntoConstraints
    -0.54
    市镇
    -0.40
    Lähteet
    -0.39
    urop
    -0.39
    AnchorStyles
    -0.38
    defaultProps
    -0.36
     سكانية
    -0.35
     wikihow
    -0.34
     monop
    -0.34
     configuration
    -0.33
    POSITIVE LOGITS
     alumni
    2.31
     Alumni
    2.06
    Alumni
    1.87
     alumnus
    1.85
    alumni
    1.85
     alum
    1.68
     ALUM
    1.61
     reunion
    1.45
     graduates
    1.41
     Alum
    1.40
    Activations Density 0.207%

    No Known Activations