© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 7156
    Prev
    Next
    INDEX
    Explanations

    phrases related to the evaluation and assessment of studies or methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    -0.74
    .
    -0.65
     both
    -0.65
     the
    -0.63
     
    -0.59
     that
    -0.58
     a
    -0.57
     in
    -0.57
    ↵
    -0.57
    ↵↵
    -0.57
    POSITIVE LOGITS
    Autoritní
    1.34
    帖最后由
    1.32
     autorytatywna
    1.26
    +#+#
    1.25
    LookAnd
    1.24
    afficheront
    1.23
    sizeCache
    1.22
    GEBURTSDATUM
    1.22
    Geplaatst
    1.22
    Personensuche
    1.19
    Activations Density 1.671%

    No Known Activations