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. 117276
    Prev
    Next
    INDEX
    Explanations

    terms related to publishing and articles in an online context

    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
    awtextra
    -0.40
    ilaian
    -0.38
     graduación
    -0.38
    Indirect
    -0.36
    protetor
    -0.36
     comédie
    -0.35
     Summe
    -0.35
     roupa
    -0.35
     Krankheit
    -0.35
     psychi
    -0.35
    POSITIVE LOGITS
     nakalista
    0.60
    PerformLayout
    0.57
    msgTypes
    0.57
    uxxxx
    0.54
    sidemargin
    0.53
    RectangleBorder
    0.53
     StringTokenizer
    0.53
    
    0.52
     שוליים
    0.51
     ExecuteAsync
    0.49
    Activations Density 0.013%

    No Known Activations