© 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. 15-GEMMASCOPE-RES-16K
    11. 11248
    Prev
    Next
    INDEX
    Explanations

    operations related to text and string manipulation using regular expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     parma
    -0.51
     leased
    -0.47
     出版
    -0.44
     Leila
    -0.43
    GeneratedMessage
    -0.43
    rů
    -0.43
    ')[
    -0.42
     inventory
    -0.42
    %);
    -0.42
     papers
    -0.42
    POSITIVE LOGITS
    ThroughAttribute
    0.71
     Replace
    0.66
     remplacé
    0.66
     remplace
    0.63
    LookAnd
    0.61
     beginnetje
    0.60
     replaces
    0.59
    COUVER
    0.59
     replace
    0.58
     Lightboxes
    0.58
    Activations Density 0.468%

    No Known Activations