© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 5693
    Prev
    Next
    INDEX
    Explanations

    instances of possessive nouns and associated permissions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Begriffsklä
    -0.51
     disambiguazione
    -0.49
    PhysRev
    -0.44
     Waray
    -0.44
    Orient
    -0.43
     Zimbabwe
    -0.42
     Orient
    -0.41
    Drift
    -0.41
    Deliver
    -0.41
     Deliver
    -0.41
    POSITIVE LOGITS
    addPreferredGap
    0.59
    addGap
    0.47
    HasAnnotation
    0.46
     permintaan
    0.42
     erklär
    0.38
    LabelTagHelper
    0.38
     thanks
    0.37
     aided
    0.36
    Tembelea
    0.35
     fără
    0.35
    Activations Density 0.270%

    No Known Activations