© 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. 2-GEMMASCOPE-RES-16K
    11. 4585
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "missing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.98
    ArrowToggle
    -0.87
     BorderRadius
    -0.76
    XtraEditors
    -0.72
     שוליים
    -0.71
    adaptiveStyles
    -0.71
    发表于
    -0.71
    IVEREF
    -0.70
    hdashline
    -0.70
    dymyr
    -0.69
    POSITIVE LOGITS
     missing
    3.66
     Missing
    3.33
    Missing
    3.25
    missing
    3.23
     MISSING
    3.06
    MISSING
    2.53
     absent
    1.55
     lacking
    1.53
     fehl
    1.30
     manquante
    1.30
    Activations Density 0.101%

    No Known Activations