© 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. 24-GEMMASCOPE-RES-16K
    11. 12307
    Prev
    Next
    INDEX
    Explanations

    attributes and metadata related to assembly configurations and documentation in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    C# attributes

    np_acts-logits-general · gemini-2.0-flash

    C# attributes in square brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Enllaces
    -0.66
    "}>
    -0.65
     ');
    -0.63
    AnimationsModule
    -0.63
    >');
    -0.62
    '});
    -0.60
    WebpackPlugin
    -0.60
    ''');
    -0.58
    Erreferentziak
    -0.58
     mxArray
    -0.57
    POSITIVE LOGITS
    Attribute
    0.90
     Attribute
    0.70
     attribute
    0.69
    attribute
    0.66
     ModelExpression
    0.60
    Attr
    0.57
    Att
    0.56
     attributes
    0.54
    attr
    0.52
     RVA
    0.51
    Activations Density 0.063%

    No Known Activations