© 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. 2138
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references in texts

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

    prepositional phrases and conjunctions that connect clauses or indicate relationships between nouns and other elements.

    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
     usarlo
    -0.38
    身边的
    -0.37
    体を
    -0.35
     conosco
    -0.35
    体は
    -0.34
     contigo
    -0.34
    因为它
    -0.33
     इसे
    -0.32
    selves
    -0.32
     piacere
    -0.32
    POSITIVE LOGITS
     deren
    1.00
     peoples
    0.97
     dessen
    0.92
     his
    0.86
    对方的
    0.79
     childrens
    0.78
    大家的
    0.74
     THEIR
    0.73
     hänen
    0.72
     HIS
    0.70
    Activations Density 1.588%

    No Known Activations