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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 58219
    Prev
    Next
    INDEX
    Explanations

    concepts related to customer satisfaction

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

    customer satisfaction and patient satisfaction

    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
     tag
    -0.44
    Besos
    -0.43
    Datuak
    -0.43
    الدراسه
    -0.43
     shell
    -0.43
     slug
    -0.42
     link
    -0.41
    gather
    -0.40
     ponder
    -0.40
    ses
    -0.39
    POSITIVE LOGITS
     satisfaction
    0.79
    satisfaction
    0.76
     Satisfaction
    0.74
    Satisfaction
    0.68
     satisfacción
    0.64
    atisfaction
    0.62
     satisfecho
    0.60
    满意
    0.57
     tevreden
    0.56
     dissatisfaction
    0.52
    Activations Density 0.007%

    No Known Activations