© 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. 7500
    Prev
    Next
    INDEX
    Explanations

    intense expressions related to food quality and opinions

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

    Following "be" and forms of "to be"

    np_acts-logits-general · gemini-2.0-flash

    exaggeration, understatement, too, bluntly

    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
    tahui
    -0.84
     nakalista
    -0.72
    ⓧ
    -0.71
    Билгалдахарш
    -0.64
     Numerade
    -0.63
     <=",
    -0.58
     estekak
    -0.56
    ậy
    -0.56
    thenReturn
    -0.56
    🔕
    -0.54
    POSITIVE LOGITS
     exaggeration
    0.88
     exaggerating
    0.84
     exaggerate
    0.82
     exagger
    0.77
     exager
    0.72
     exag
    0.70
     stretching
    0.68
     hyper
    0.68
     understatement
    0.67
     stretch
    0.66
    Activations Density 0.282%

    No Known Activations