© 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. 20-GEMMASCOPE-RES-16K
    11. 12280
    Prev
    Next
    INDEX
    Explanations

    instances of the word "read" and its variations

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

    Text beginning with "Read"

    np_acts-logits-general · gemini-2.0-flash

    reading text or commands

    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
    帖最后由
    -0.90
     MonoBehaviour
    -0.86
    Jegyzetek
    -0.73
    ConstraintMaker
    -0.72
     AppCompatTheme
    -0.69
    makeConstraints
    -0.66
    ButterKnife
    -0.64
    umably
    -0.62
    IntoConstraints
    -0.62
    enumii
    -0.61
    POSITIVE LOGITS
     aloud
    0.97
    justed
    0.89
     reads
    0.86
     Readers
    0.82
     Reader
    0.81
    Читайте
    0.80
     Reads
    0.78
     READ
    0.77
    reads
    0.76
     readers
    0.76
    Activations Density 0.123%

    No Known Activations