© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 11021
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'recognition' and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    шаго
    -0.71
    gdx
    -0.71
     allons
    -0.70
     المعيارى
    -0.68
    rosophila
    -0.68
    ortiment
    -0.66
    fvar
    -0.65
     Tull
    -0.64
    الثة
    -0.64
     âgées
    -0.64
    POSITIVE LOGITS
     recognition
    2.13
     recogni
    2.09
     recognise
    2.00
     recognize
    1.98
     RECOGN
    1.97
     recognised
    1.93
     recognising
    1.90
     recognized
    1.90
     recognizing
    1.88
     Recognition
    1.87
    Activations Density 0.057%

    No Known Activations