© 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. 16-GEMMASCOPE-RES-16K
    11. 7086
    Prev
    Next
    INDEX
    Explanations

    references to thinness or thin objects

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

    "thin" and its related concepts

    np_acts-logits-general · gemini-2.0-flash

    thinness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ">//
    -0.86
    esModule
    -0.83
    ]")]
    -0.82
    oredCriteria
    -0.80
    MLLoader
    -0.80
     StatefulWidget
    -0.76
    RegressionTest
    -0.76
    calaure
    -0.74
    AnchorTagHelper
    -0.73
     continúas
    -0.69
    POSITIVE LOGITS
    Thin
    1.19
     Thin
    1.15
     thin
    1.14
     thick
    0.97
     thickness
    0.96
    thin
    0.95
    thick
    0.94
    thickness
    0.88
    Thick
    0.86
     thinning
    0.86
    Activations Density 0.106%

    No Known Activations