© 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. 15-GEMMASCOPE-RES-16K
    11. 4510
    Prev
    Next
    INDEX
    Explanations

    references to fields or categories of inventions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getSystemService
    -0.85
    AndEndTag
    -0.85
    migrationBuilder
    -0.72
     GenerationType
    -0.70
     mourut
    -0.69
     HFILL
    -0.69
     متعلقه
    -0.67
    fjspx
    -0.67
    mappedBy
    -0.66
     MainAxisSize
    -0.65
    POSITIVE LOGITS
     previous
    1.61
     existing
    1.53
    Previous
    1.45
     Previous
    1.43
     Existing
    1.39
    previous
    1.36
    Existing
    1.35
     already
    1.34
    existing
    1.29
     previously
    1.29
    Activations Density 0.515%

    No Known Activations