© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 7435
    Prev
    Next
    INDEX
    Explanations

    descriptions of different varieties of fruits, especially relating to their characteristics and comparisons

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    fruit or fruit varieties

    np_acts-logits-general · gemini-2.0-flash

    fruit and pear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    RenderAtEndOf
    -0.65
    SharedCtor
    -0.64
    RegressionTest
    -0.58
    MessageTagHelper
    -0.56
    SharedDtor
    -0.52
    ensement
    -0.52
    IntoConstraints
    -0.52
     '\\;'
    -0.52
     насељу
    -0.51
    RegistryLite
    -0.50
    POSITIVE LOGITS
     fruit
    1.41
     Fruit
    1.12
     fruits
    1.12
    fruit
    1.08
    Fruit
    1.05
     FRUIT
    1.02
     fruta
    0.94
     frukt
    0.93
     Fruits
    0.93
     ripen
    0.89
    Activations Density 0.189%

    No Known Activations