© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10557
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to medical cells and their functions

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

    after certain prefixes or suffixes

    np_acts-logits-general · gemini-2.0-flash

    positive words

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     &___
    -0.45
    Exploration
    -0.43
     Exploration
    -0.40
    itinéraire
    -0.39
     exploration
    -0.39
     AlertDialog
    -0.39
     cof
    -0.38
    ---*/
    -0.38
    RTDA
    -0.38
     autorytatywna
    -0.37
    POSITIVE LOGITS
     positif
    0.53
     positivos
    0.50
     positive
    0.49
     positiva
    0.45
     positivo
    0.44
     deportivos
    0.44
     heridos
    0.44
     Infór
    0.44
     embarazada
    0.43
     stră
    0.43
    Activations Density 1.091%

    No Known Activations