© 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. 2360
    Prev
    Next
    INDEX
    Explanations

    details about clothing and insignia, particularly those that signify affiliation or membership

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

    text containing organizational logos, emblems, and identifying marks on clothing or materials.

    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
    تقاوى
    -0.66
    enumii
    -0.57
     يتيمه
    -0.55
     Signalez
    -0.52
     tartalomajánló
    -0.51
     CommonModule
    -0.51
     iconLine
    -0.50
     otomatig
    -0.50
    Sucesor
    -0.49
    providedIn
    -0.48
    POSITIVE LOGITS
     inscription
    0.88
     engraved
    0.87
     printed
    0.86
     inscriptions
    0.84
     inscribed
    0.82
     written
    0.81
     imprinted
    0.78
    engra
    0.76
     embossed
    0.76
    written
    0.76
    Activations Density 0.348%

    No Known Activations