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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14359
    Prev
    Next
    INDEX
    Explanations

    terms related to optical systems and their measurements

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

    light reflection/deflection

    np_acts-logits-general · gemini-2.0-flash

    light beam focusing and deflection

    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
    сылкі
    -0.63
     estekak
    -0.57
    đu
    -0.55
    ConstraintMaker
    -0.52
     Sleeps
    -0.52
    downe
    -0.49
     Lasting
    -0.49
     lasting
    -0.48
     Jump
    -0.47
    atguigu
    -0.46
    POSITIVE LOGITS
     diffraction
    0.74
     Fres
    0.73
     incident
    0.72
     light
    0.72
    Fres
    0.68
     reflected
    0.68
     rays
    0.67
     beam
    0.65
     Snell
    0.65
     Huy
    0.65
    Activations Density 1.111%

    No Known Activations