Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 11083
    Prev
    Next
    INDEX
    Explanations

    terms related to contemporary and modern themes in cultural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StringField
    -0.63
     Rs
    -0.62
    psack
    -0.60
     spéciaux
    -0.60
     fédé
    -0.59
     Ruiz
    -0.58
     alimentaire
    -0.58
     Sgt
    -0.57
    Rs
    -0.56
     nisso
    -0.56
    POSITIVE LOGITS
     contemporary
    2.84
     Contemporary
    2.71
    contemporary
    2.65
    Contemporary
    2.63
     CONTEM
    2.19
     contempor
    2.05
     contemporánea
    2.04
     contemporain
    1.96
     contemporáneo
    1.94
     contemporaine
    1.87
    Activations Density 0.056%

    No Known Activations