© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3242
    Prev
    Next
    INDEX
    Explanations

    syntax related to programming structures and data types in code

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

    Floating-point numbers (float, double)

    np_acts-logits-general · gemini-2.0-flash

    numeric types: float, double, int

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.67
    InputLabel
    -0.65
    IContainer
    -0.63
    SharedDtor
    -0.62
    QPalette
    -0.59
    ingu
    -0.58
    
    -0.57
    WithIOException
    -0.54
     ErrIntOverflow
    -0.53
    writeInt
    -0.53
    POSITIVE LOGITS
     float
    1.84
    double
    1.79
    float
    1.79
     double
    1.78
     Double
    1.44
    Double
    1.41
     floats
    1.38
     Float
    1.36
     DOUBLE
    1.32
     floating
    1.31
    Activations Density 0.370%

    No Known Activations