© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 3269
    Prev
    Next
    INDEX
    Explanations

    forms of the word "recognize" and its derivatives

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "recognize" and its inflections

    np_acts-logits-general · gemini-2.0-flash

    recognition of facts or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Билгалдахарш
    -0.81
    providedIn
    -0.74
     المعيارى
    -0.71
     âgées
    -0.71
    AndEndTag
    -0.70
    sidemargin
    -0.67
    AutoScaleMode
    -0.67
    VIAF
    -0.66
     âgé
    -0.66
    gdx
    -0.65
    POSITIVE LOGITS
     recognise
    1.20
     recognize
    1.12
     recognised
    1.10
     RECOGN
    1.07
     recognises
    1.05
     recognized
    1.03
     recognition
    1.01
     Recognized
    0.99
     recognizes
    0.99
     recognising
    0.97
    Activations Density 0.099%

    No Known Activations