© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 99
    Prev
    Next
    INDEX
    Explanations

    phrases related to flattery and admiration

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

    words that describe relationships and qualities between people

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

    expressing praise and admiration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    Geplaatst
    -0.82
    EndInit
    -0.70
    GEBURTSDATUM
    -0.67
    transQ
    -0.58
     OMITBAD
    -0.53
     desaf
    -0.53
    Grim
    -0.52
    stdc
    -0.51
    TemporalType
    -0.50
    SBATCH
    -0.50
    POSITIVE LOGITS
     praise
    2.16
     praises
    2.00
     praising
    1.98
     praised
    1.79
     compliments
    1.79
     compliment
    1.76
     Praise
    1.70
    praise
    1.66
    Praise
    1.57
     admiration
    1.48
    Activations Density 0.212%

    No Known Activations