© 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. 20-GEMMASCOPE-RES-16K
    11. 14662
    Prev
    Next
    INDEX
    Explanations

    structured data representations, such as graphs or tables

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

    Solid, dashed, dotted lines or shapes in plots

    np_acts-logits-general · gemini-2.0-flash

    solid lines and plots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.71
    mybatisplus
    -0.70
    ">//
    -0.64
    دانشنامهٔ
    -0.58
     säll
    -0.57
    ArgumentParser
    -0.57
     AssemblyTitle
    -0.56
     disambiguazione
    -0.56
     GenerationType
    -0.56
     متعلقه
    -0.56
    POSITIVE LOGITS
     dashed
    1.22
     arrows
    1.15
     dotted
    1.14
    dashed
    1.08
     shaded
    1.07
     blue
    1.06
    dotted
    1.04
     arrow
    1.00
     red
    0.99
     black
    0.98
    Activations Density 1.567%

    No Known Activations