© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 9917
    Prev
    Next
    INDEX
    Explanations

    mentions of reading or related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    -0.96
    awtextra
    -0.96
    XmlAccessType
    -0.94
    bolista
    -0.82
     MonoBehaviour
    -0.82
    LikeLike
    -0.81
    berdayakan
    -0.79
    Hauptartikel
    -0.77
    ConstraintMaker
    -0.75
    $-$\\
    -0.74
    POSITIVE LOGITS
     read
    1.66
     reads
    1.66
     reading
    1.48
     Reading
    1.41
     READ
    1.41
    read
    1.40
     Reads
    1.36
    Reading
    1.32
    Read
    1.29
    reads
    1.27
    Activations Density 0.092%

    No Known Activations