© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 35-GEMMASCOPE-RES-16K
    11. 12272
    Prev
    Next
    INDEX
    Explanations

    statements of existence or propositions involving 'is' to indicate affirmation or certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    belong
    -0.59
    encodeWith
    -0.57
     belonging
    -0.50
     принадле
    -0.46
     belong
    -0.46
     Belong
    -0.43
    belongs
    -0.41
     baz
    -0.40
    もので
    -0.40
     belongs
    -0.40
    POSITIVE LOGITS
     true
    0.90
     reflected
    0.79
     why
    0.79
     untrue
    0.75
     evidenced
    0.73
     corroborated
    0.70
    true
    0.68
     exemplified
    0.68
     truer
    0.67
     especially
    0.65
    Activations Density 0.481%

    No Known Activations