© 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. 3-GEMMASCOPE-RES-16K
    11. 1443
    Prev
    Next
    INDEX
    Explanations

    indicators of significant outcomes or conditions, especially in contexts of research or decision-making

    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
    ########.
    -0.87
     betweenstory
    -0.87
    Spoljašnje
    -0.71
     Efq
    -0.69
    windowFixed
    -0.68
    fjspx
    -0.68
     المعيارى
    -0.68
     eventdata
    -0.67
    UnusedPrivate
    -0.67
     članak
    -0.66
    POSITIVE LOGITS
     
    0.56
     the
    0.46
     “
    0.46
    Personendaten
    0.44
     It
    0.43
     י
    0.43
     hyö
    0.42
    attribution
    0.41
    ^)
    0.41
     part
    0.41
    Activations Density 0.686%

    No Known Activations