© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 51181
    Prev
    Next
    INDEX
    Explanations

    variations of the word "slightly" and its usage in describing differences

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

    slightly comparative state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     vær
    -0.43
     Inscrivez
    -0.40
     cartera
    -0.40
    ฒ
    -0.40
     Suivez
    -0.40
     praco
    -0.39
     Boek
    -0.38
    VALUE
    -0.37
    ęp
    -0.36
     Viitattu
    -0.36
    POSITIVE LOGITS
     slightly
    0.99
     Slightly
    0.96
    slightly
    0.93
     Slight
    0.90
    Slightly
    0.90
     slight
    0.81
    Slight
    0.80
    addPreferredGap
    0.73
     légèrement
    0.69
     leicht
    0.68
    Activations Density 0.009%

    No Known Activations