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

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 30555
    Prev
    Next
    INDEX
    Explanations

    the word "then" and variations of it, indicating sequential actions or events

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

    sequences of actions or events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enfans
    -0.51
     Offisielt
    -0.43
     fieltro
    -0.38
     Juifs
    -0.36
     ſeveral
    -0.36
     Füßen
    -0.36
     dieux
    -0.35
     duquel
    -0.35
     الاجتما
    -0.35
     Romains
    -0.35
    POSITIVE LOGITS
     kaarangay
    0.57
     autorytatywna
    0.56
    complexContent
    0.55
    tanleria
    0.55
     whilst
    0.50
    ulongan
    0.50
     nakalista
    0.50
    bul
    0.47
    áctenos
    0.46
     BUL
    0.45
    Activations Density 0.043%

    No Known Activations