© 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. 16-GEMMASCOPE-RES-16K
    11. 12463
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating abilities or possibilities

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

    German, French, or Norwegian text

    np_acts-logits-general · gemini-2.0-flash

    German and French grammatical structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     getP
    -0.48
    èze
    -0.47
    KEYCODE
    -0.46
    vaal
    -0.46
    setupUi
    -0.46
     että
    -0.45
    ="../
    -0.45
     solchen
    -0.45
     AttributeSet
    -0.45
     Gre
    -0.45
    POSITIVE LOGITS
     also
    1.18
     moreover
    1.02
     meanwhile
    1.01
     nevertheless
    1.01
     however
    1.01
     unfortunately
    0.97
     therefore
    0.96
     certainly
    0.95
     probably
    0.94
     evidently
    0.92
    Activations Density 0.102%

    No Known Activations