© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14581
    Prev
    Next
    INDEX
    Explanations

    sections related to data processing and analysis

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

    data analysis/processing

    np_acts-logits-general · gemini-2.0-flash

    data processing and analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spéc
    -0.54
     dejamos
    -0.52
     dimentic
    -0.47
    ovs
    -0.46
     setInterval
    -0.46
    palen
    -0.45
     volontaire
    -0.45
    новниш
    -0.45
     remplacé
    -0.45
     abandonné
    -0.44
    POSITIVE LOGITS
     processing
    1.30
     processed
    1.25
     Processing
    1.24
    Processing
    1.12
    processing
    1.10
     Processed
    1.09
     PROCESSING
    1.09
     analyzed
    1.02
    processed
    1.01
    Processed
    0.96
    Activations Density 0.671%

    No Known Activations