© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3918
    Prev
    Next
    INDEX
    Explanations

    expressions and metrics related to customer satisfaction and service quality

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

    before or related to satisfaction

    np_acts-logits-general · gemini-2.0-flash

    degree of satisfaction or happiness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Weakness
    -0.63
    rotech
    -0.59
    ::$_
    -0.56
    Weakness
    -0.56
     InputDecoration
    -0.55
     vulnerability
    -0.55
     Paglinawan
    -0.55
     Caution
    -0.54
    ApiModelProperty
    -0.54
     weakness
    -0.53
    POSITIVE LOGITS
     happy
    2.56
     satisfied
    2.51
     satisfaction
    2.37
    happy
    2.25
     Happy
    2.21
    Happy
    2.15
     Satisfied
    2.14
     happiness
    2.12
    satisfied
    2.08
     HAPPY
    2.05
    Activations Density 0.216%

    No Known Activations