© 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. 24-GEMMASCOPE-RES-16K
    11. 10749
    Prev
    Next
    INDEX
    Explanations

    structured programming elements and language syntax

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

    Java types (boolean, int, String, etc.)

    np_acts-logits-general · gemini-2.0-flash

    Java declarations and types

    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
     const
    -0.65
     bool
    -0.62
    foreach
    -0.56
     AspNetCore
    -0.54
    nullptr
    -0.53
    makeConstraints
    -0.53
    bool
    -0.52
     nullptr
    -0.51
    AspNetCore
    -0.51
    NULL
    -0.51
    POSITIVE LOGITS
    final
    1.02
    String
    1.02
     String
    1.02
    boolean
    1.01
     final
    0.99
     boolean
    0.90
    byte
    0.84
    Integer
    0.81
     Integer
    0.80
     Object
    0.79
    Activations Density 0.196%

    No Known Activations