© 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
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 8915
    Prev
    Next
    INDEX
    Explanations

    punctuation marks in code or documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poveznice
    -0.58
     ſche
    -0.57
     enfans
    -0.54
     canst
    -0.53
     pleaſure
    -0.52
     pungkasnya
    -0.52
     bakgrund
    -0.51
     ſta
    -0.50
     betrekking
    -0.50
    ImageContext
    -0.49
    POSITIVE LOGITS
    ://
    0.61
    fasterxml
    0.56
    baomidou
    0.55
     للاسماء
    0.50
    بوابة
    0.47
    companies
    0.47
     informée
    0.46
     companies
    0.46
    EnableWeb
    0.45
    يميديا
    0.45
    Activations Density 0.025%

    No Known Activations