© 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. 24-GEMMASCOPE-RES-16K
    11. 14759
    Prev
    Next
    INDEX
    Explanations

    journalistic language that discusses accountability and the perception of legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows a sentence ending

    np_acts-logits-general · gemini-2.0-flash

    followed by conjunctions or prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fijar
    -0.57
     liée
    -0.56
     goûts
    -0.55
     liées
    -0.55
     uș
    -0.52
     vrais
    -0.49
     úteis
    -0.49
     a
    -0.48
     atuais
    -0.47
    new
    -0.47
    POSITIVE LOGITS
     للمعارف
    1.16
     themſelves
    1.14
    
    1.11
     Monfieur
    1.08
    #+#
    1.08
     purpoſe
    1.06
     pleaſure
    1.05
    ंदीखरीदारी
    1.04
    RectangleBorder
    1.02
    AddTagHelper
    1.01
    Activations Density 0.270%

    No Known Activations