© 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. 22-GEMMASCOPE-RES-16K
    6. 14353
    Prev
    Next
    INDEX
    Explanations

    academic terms and phrases related to discussion, analysis, and critique within a structured context

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

    followed by verbs

    np_acts-logits-general · gemini-2.0-flash

    pronouns followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chré
    -0.77
     démocr
    -0.75
     vectorielles
    -0.75
     blessés
    -0.71
     enfans
    -0.70
    IntoConstraints
    -0.68
     financières
    -0.68
     définiti
    -0.68
     ouvriers
    -0.68
     critères
    -0.68
    POSITIVE LOGITS
     gets
    1.13
     takes
    1.13
     makes
    1.08
     puts
    1.04
     starts
    1.02
     goes
    1.01
     tries
    0.99
     builds
    0.99
     finds
    0.98
     creates
    0.98
    Activations Density 2.750%

    No Known Activations