© 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. 13-GEMMASCOPE-RES-16K
    6. 9003
    Prev
    Next
    INDEX
    Explanations

    terms related to concise summaries and reports in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     constantemente
    -0.29
     constantly
    -0.28
    HasColumnName
    -0.28
     abrazo
    -0.28
    clearpage
    -0.27
     perfectamente
    -0.26
     exactement
    -0.26
     žád
    -0.26
     muchas
    -0.26
     tiks
    -0.26
    POSITIVE LOGITS
    Brief
    0.90
     briefly
    0.89
     rudimentary
    0.87
    OGND
    0.82
     Brief
    0.81
     brief
    0.80
    brief
    0.80
    tagHelperRunner
    0.78
     linkovi
    0.77
    Informal
    0.76
    Activations Density 0.711%

    No Known Activations