© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 59059
    Prev
    Next
    INDEX
    Explanations

    conjunctions and linking phrases throughout the text

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

    connecting formal english phrases

    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
     smarter
    -0.53
     gossi
    -0.49
     smir
    -0.46
     spooky
    -0.43
     crazy
    -0.43
     wacky
    -0.43
     savvy
    -0.43
     tricky
    -0.42
     Gos
    -0.42
     scary
    -0.41
    POSITIVE LOGITS
    rungsseite
    0.71
     provided
    0.59
     Administrativna
    0.59
     MainAxisSize
    0.57
     ſind
    0.55
     magnétique
    0.54
     ilustracja
    0.54
     wijze
    0.52
     pertanto
    0.52
     miniaturka
    0.52
    Activations Density 0.152%

    No Known Activations