© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12150
    Prev
    Next
    INDEX
    Explanations

    phrases that express personal feelings or emotional states

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

    Expressing unwillingness or reluctance

    np_acts-logits-general · gemini-2.0-flash

    don't want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Italijanski
    -0.47
    IDX
    -0.46
     yyhl
    -0.45
    Населення
    -0.43
    InitVars
    -0.41
    曖昧さ回避
    -0.40
    SpringRunner
    -0.40
     unsur
    -0.40
     silo
    -0.38
    Individual
    -0.38
    POSITIVE LOGITS
    不想
    0.73
     unwilling
    0.66
     reluctance
    0.59
     reluctant
    0.58
    不愿
    0.56
     unwillingness
    0.55
    せっかく
    0.54
     Schließlich
    0.54
     nech
    0.53
    たくない
    0.52
    Activations Density 0.261%

    No Known Activations