© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 70940
    Prev
    Next
    INDEX
    Explanations

    phrases that reference rewards and incentives associated with actions or behaviors

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

    for reward or success

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    レスレット
    -0.38
     hâte
    -0.35
    どうぞ
    -0.35
    cuál
    -0.34
    借助
    -0.33
    hmigung
    -0.32
    のでは
    -0.32
     mulig
    -0.32
    失礼
    -0.31
    といけない
    -0.31
    POSITIVE LOGITS
     successful
    0.68
     efforts
    0.66
     effort
    0.63
     successfully
    0.62
    effort
    0.60
    successful
    0.60
    efforts
    0.59
     kasarigan
    0.59
    Successful
    0.56
     erfolgreichen
    0.56
    Activations Density 0.052%

    No Known Activations