© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 87
    Prev
    Next
    INDEX
    Explanations

    numerical values and comparisons related to thresholds or levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <_>
    -0.52
    argout
    -0.51
     ines
    -0.50
    rsiniz
    -0.49
    bius
    -0.48
     ages
    -0.48
    Entities
    -0.47
    HWND
    -0.46
     StringVar
    -0.46
     Polskiego
    -0.44
    POSITIVE LOGITS
     exceeds
    1.01
     exceeded
    1.00
     exceeding
    0.99
     exceed
    0.98
     surpassing
    0.89
     surpasses
    0.88
     surpassed
    0.87
     surpass
    0.83
     ویکی‌پدیا
    0.78
     dépass
    0.78
    Activations Density 0.536%

    No Known Activations