Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 113613
    Prev
    Next
    INDEX
    Explanations

    sentence structures and punctuation in written text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noDo
    -0.67
     ivelany
    -0.61
     preventative
    -0.60
     supplemental
    -0.58
     census
    -0.54
    banken
    -0.52
    OGND
    -0.51
     poul
    -0.50
     scent
    -0.49
     dentures
    -0.49
    POSITIVE LOGITS
     Wiktionnaire
    0.60
    帖最后由
    0.52
    новништво
    0.50
    发表于
    0.49
    AnimationsModule
    0.49
     tartalomajánló
    0.46
    Moreover
    0.45
     parallèle
    0.45
     Derfor
    0.45
     principio
    0.43
    Activations Density 0.003%

    No Known Activations