© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 9349
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating future actions or possibilities

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

    Preceding "be" or a modal verb

    np_acts-logits-general · gemini-2.0-flash

    modal verbs followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArrowToggle
    -0.47
     fuch
    -0.36
    abestanden
    -0.35
    ,...
    -0.35
     fays
    -0.34
    wpi
    -0.34
    Халык
    -0.34
     hof
    -0.34
    gunt
    -0.32
     servent
    -0.32
    POSITIVE LOGITS
     be
    1.13
     also
    0.88
     have
    0.87
     always
    0.85
     certainly
    0.79
     actually
    0.74
     become
    0.73
     never
    0.72
     surely
    0.71
     not
    0.70
    Activations Density 0.796%

    No Known Activations