© 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. 20-GEMMASCOPE-RES-16K
    11. 12333
    Prev
    Next
    INDEX
    Explanations

    words and phrases that express certainty or emphasis

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

    preceding present-tense verbs

    np_acts-logits-general · gemini-2.0-flash

    adverb followed by verb

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     serem
    -0.63
     sighing
    -0.52
     clarification
    -0.52
     fouling
    -0.50
     spotting
    -0.50
     scrambling
    -0.49
     informing
    -0.49
     tracing
    -0.47
     whispering
    -0.47
     robbing
    -0.46
    POSITIVE LOGITS
     has
    1.07
     got
    1.04
     had
    1.03
     is
    1.00
     took
    0.99
     can
    0.97
     went
    0.96
     seems
    0.94
     makes
    0.92
     came
    0.92
    Activations Density 0.312%

    No Known Activations