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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 131049
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to microscopy and molecular electronics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     year
    -0.37
     CommonModule
    -0.36
    proportion
    -0.36
     NgModule
    -0.35
    NgModule
    -0.35
     vet
    -0.35
     parlato
    -0.34
    tvguidetime
    -0.33
     Particip
    -0.32
     voted
    -0.32
    POSITIVE LOGITS
    adaptiveStyles
    0.60
    httphttps
    0.56
    RectangleBorder
    0.54
    쿵
    0.51
    Skocz
    0.50
    romyalgia
    0.50
    ccato
    0.50
     onPostExecute
    0.49
     unangemessene
    0.49
    mgang
    0.48
    Activations Density 0.066%

    No Known Activations