© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 3665
    Prev
    Next
    INDEX
    Explanations

    affirmations and confirmations in dialogue

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

    Affirmative responses or agreement

    np_acts-logits-general · gemini-2.0-flash

    affirmative confirmation

    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
     estekak
    -0.61
     <>",
    -0.47
    ніципалі
    -0.43
    adaptiveStyles
    -0.43
    MigrationBuilder
    -0.39
     swing
    -0.38
    évaluateur
    -0.38
     Swing
    -0.38
    umblr
    -0.38
    aragus
    -0.37
    POSITIVE LOGITS
     yes
    2.00
     Yes
    1.72
    Yes
    1.71
    yes
    1.66
     yep
    1.55
     Yep
    1.48
     yeah
    1.48
    Yep
    1.45
     YES
    1.43
    没错
    1.39
    Activations Density 0.197%

    No Known Activations