© 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 EvalsExportsAPI 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. 2932
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to data analysis and device functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical and analytical language related to performance measurements and evaluations

    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
    (({
    -0.37
     verbunden
    -0.36
     سب
    -0.36
    Pr
    -0.36
     I
    -0.35
    skem
    -0.35
    ector
    -0.34
    ↵
    -0.34
     earlier
    -0.34
    ://
    -0.34
    POSITIVE LOGITS
     newOwner
    1.08
     new
    1.02
    新的
    1.00
     nuevos
    0.95
     nieuwe
    0.94
    tvguidetime
    0.94
     ویکی‌پدی
    0.92
     afresh
    0.92
     Roskov
    0.91
     newArray
    0.89
    Activations Density 1.187%

    No Known Activations