© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 6098
    Prev
    Next
    INDEX
    Explanations

    key concepts related to the structure and themes of projects or organized events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     csal
    -0.46
    струкция
    -0.45
    Ử
    -0.44
     فعل
    -0.44
    Recognition
    -0.43
     Bennett
    -0.42
    eira
    -0.42
    fsch
    -0.41
    перь
    -0.41
    /******/
    -0.41
    POSITIVE LOGITS
     topic
    2.83
     theme
    2.79
     topics
    2.65
     themes
    2.60
     Topic
    2.41
     thème
    2.28
     Theme
    2.27
    Topic
    2.25
    topic
    2.17
     subject
    2.16
    Activations Density 0.371%

    No Known Activations