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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 12747
    Prev
    Next
    INDEX
    Explanations

    technical terms and code related to JavaScript libraries and frameworks

    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
     nahilalakip
    -0.85
    StoryboardSegue
    -0.80
    +#+#
    -0.77
    writerow
    -0.71
    lapsingToolbar
    -0.70
    rifice
    -0.68
    IntoConstraints
    -0.66
     MainAxisSize
    -0.65
     OnDestroy
    -0.65
     Shoemaker
    -0.64
    POSITIVE LOGITS
    jquery
    1.57
     jquery
    1.14
     jQuery
    0.90
    jQuery
    0.69
    δή
    0.56
    zzarella
    0.55
     Pek
    0.55
    нциклопедия
    0.54
     купе
    0.54
     ajax
    0.52
    Activations Density 0.063%

    No Known Activations