© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19-GEMMASCOPE-RES-16K
    11. 14974
    Prev
    Next
    INDEX
    Explanations

    code-related elements such as file names, data types, and variable declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    -0.64
    ’
    -0.56
     
    -0.53
     "
    -0.52
    <eos>
    -0.48
     Price
    -0.48
    UTELY
    -0.48
    <>();
    -0.47
     “
    -0.46
     a
    -0.46
    POSITIVE LOGITS
     CreateTagHelper
    1.10
    TagMode
    1.00
    تقاوى
    0.99
     ModelExpression
    0.99
    Personendaten
    0.98
     Chwiliwch
    0.96
    ьаж
    0.92
    SharedDtor
    0.87
     resourceCulture
    0.86
    IntoConstraints
    0.86
    Activations Density 0.494%

    No Known Activations