© 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. 11-GEMMASCOPE-RES-16K
    11. 6974
    Prev
    Next
    INDEX
    Explanations

    negation and comparative phrases that indicate opposition or contrast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.53
    PullParser
    -0.52
     pleaſure
    -0.50
     otomatig
    -0.46
    Numerade
    -0.45
     houſe
    -0.41
    decla
    -0.40
    TargetApi
    -0.40
    VIAF
    -0.40
     purpoſe
    -0.40
    POSITIVE LOGITS
    而非
    0.71
    而不是
    0.69
     وليس
    0.60
     anstatt
    0.56
     rather
    0.51
     bukan
    0.48
    principalColumn
    0.45
     ולא
    0.45
     dibanding
    0.44
     zamiast
    0.44
    Activations Density 0.343%

    No Known Activations