© 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. 24-GEMMASCOPE-RES-16K
    11. 6470
    Prev
    Next
    INDEX
    Explanations

    intensifying adverbs, particularly "very."

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

    Follows intensifiers (very, extremely, quite, rather)

    np_acts-logits-general · gemini-2.0-flash

    adverbs of degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.49
    writeFieldEnd
    -0.48
     themſelves
    -0.43
    hede
    -0.42
     cauſe
    -0.41
    shape
    -0.41
    shaped
    -0.41
     Ausrüstung
    -0.39
     biais
    -0.39
    openConnection
    -0.39
    POSITIVE LOGITS
     very
    1.06
     Very
    0.98
     VERY
    0.96
    Very
    0.91
    very
    0.90
    VERY
    0.87
    Molto
    0.78
    очень
    0.73
    Sehr
    0.70
     Molto
    0.70
    Activations Density 0.153%

    No Known Activations