© 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. 8629
    Prev
    Next
    INDEX
    Explanations

    references to the main purpose or focus of a study or document

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

    demonstrative pronouns or articles ("this") at the beginning of descriptive passages.

    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
     Hälfte
    -0.45
    zelfde
    -0.41
     helft
    -0.41
     poszczegól
    -0.39
     najważ
    -0.39
     religiosos
    -0.38
     plupart
    -0.37
     wichtigste
    -0.37
     perfección
    -0.37
     suficiente
    -0.37
    POSITIVE LOGITS
     documentary
    1.10
     book
    1.07
     booklet
    1.02
     podcast
    1.02
     webinar
    1.00
     pamphlet
    0.98
     anthology
    0.97
     cookbook
    0.95
     article
    0.94
     books
    0.94
    Activations Density 1.046%

    No Known Activations