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. 16-GEMMASCOPE-RES-16K
    6. 13195
    Prev
    Next
    INDEX
    Explanations

    structural elements in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bì
    -0.57
     SwitchCompat
    -0.51
    AnchorTagHelper
    -0.49
     MEDIT
    -0.49
    werte
    -0.48
     plastiques
    -0.46
     elettron
    -0.46
     faudrait
    -0.46
    +#+#
    -0.45
     statistiques
    -0.44
    POSITIVE LOGITS
     وتسجيلات
    0.78
    SBATCH
    0.68
    ConstraintMaker
    0.65
    出版年
    0.64
    ésultat
    0.63
     الرياضيه
    0.63
    IntoConstraints
    0.63
     autorytatywna
    0.63
    BibitemShut
    0.61
    principalColumn
    0.61
    Activations Density 0.199%

    No Known Activations