© 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. 10866
    Prev
    Next
    INDEX
    Explanations

    elements of code structure, particularly focusing on classes and their closure

    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
     MessageBoxIcon
    -0.60
    談社
    -0.59
    
    -0.57
    mtrl
    -0.54
    WithIOException
    -0.53
     lòng
    -0.52
    addCriterion
    -0.51
    ANTLR
    -0.51
     '',
    -0.50
    urgis
    -0.49
    POSITIVE LOGITS
     ویکی‌پدیای
    0.85
     صوتيه
    0.62
    <eos>
    0.59
    KURZBESCHREIBUNG
    0.54
     automatiques
    0.54
     femininos
    0.52
    complexType
    0.52
    findpost
    0.51
     تكبرها
    0.51
     дописавши
    0.50
    Activations Density 0.020%

    No Known Activations