© 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. 13-GEMMASCOPE-RES-16K
    11. 7451
    Prev
    Next
    INDEX
    Explanations

    past tense and participial verbs indicating visual perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    localctx
    -0.51
     quitté
    -0.44
     twij
    -0.44
    mobileqq
    -0.41
     mijne
    -0.41
     fijn
    -0.40
     התק
    -0.40
     verbonden
    -0.40
     agrícolas
    -0.38
    INSEE
    -0.38
    POSITIVE LOGITS
    Seen
    1.14
     seen
    1.13
     seeing
    1.11
    seen
    1.08
    Saw
    1.06
    saw
    1.06
     saw
    1.05
     Seen
    1.03
     sees
    1.02
     Seeing
    1.02
    Activations Density 0.196%

    No Known Activations