© 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. 4821
    Prev
    Next
    INDEX
    Explanations

    explanations or justifications for various situations or phenomena

    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
    -0.78
     unknownFields
    -0.77
    stateProvider
    -0.75
    "]);
    -0.74
     الحره
    -0.73
    IsMutable
    -0.72
    Démographie
    -0.71
     propOrder
    -0.70
     चीज़ों
    -0.70
    httphttps
    -0.70
    POSITIVE LOGITS
     reason
    2.89
    reason
    2.52
     reasons
    2.48
     Reason
    2.44
    Reason
    2.42
     REASON
    2.23
    reasons
    2.10
     Reasons
    2.07
    Reasons
    2.01
    REASON
    2.00
    Activations Density 0.120%

    No Known Activations