© 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. 3-GEMMASCOPE-RES-16K
    11. 7391
    Prev
    Next
    INDEX
    Explanations

    modal verbs and their conjugations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
    verwijspagina
    -0.64
     ſte
    -0.62
    ſelves
    -0.60
     faſt
    -0.59
     AttributeSet
    -0.57
    thâu
    -0.56
     ſta
    -0.53
     ModelExpression
    -0.52
    ähteet
    -0.52
     pleaſure
    -0.52
    POSITIVE LOGITS
     werden
    2.17
     wird
    1.96
     wurde
    1.72
     worden
    1.69
     werd
    1.67
     wordt
    1.67
     wurden
    1.63
    wird
    1.45
    werden
    1.41
    wurde
    1.36
    Activations Density 0.047%

    No Known Activations