© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 52682
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cheer" and its variations, indicating themes of encouragement and support

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

    cheer someone up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orghini
    -0.54
     Dominguez
    -0.53
    Dakota
    -0.52
     delt
    -0.48
     Mino
    -0.48
     Lamont
    -0.47
    `.`
    -0.46
     насеље
    -0.46
     Dakota
    -0.45
    Rodrigo
    -0.44
    POSITIVE LOGITS
    Cheer
    1.13
     Cheer
    1.03
     cheer
    1.01
    cheer
    0.94
     cheering
    0.81
     avoient
    0.79
     pleaſure
    0.79
     cheered
    0.78
    arangay
    0.78
     Reſ
    0.78
    Activations Density 0.002%

    No Known Activations