© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6863
    Prev
    Next
    INDEX
    Explanations

    references to statistical data and comparisons between groups

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

    Followed by a group label

    np_acts-logits-general · gemini-2.0-flash

    classification into specific groups

    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
     disambiguazione
    -0.56
    Carriera
    -0.55
     Protección
    -0.51
     nawr
    -0.50
    例句
    -0.50
     мәкал
    -0.48
    Success
    -0.47
     clubs
    -0.47
    clubs
    -0.47
    PAREN
    -0.47
    POSITIVE LOGITS
     Court
    0.82
     Station
    0.79
     School
    0.79
     Group
    0.78
     Unit
    0.76
     Church
    0.76
     Houſe
    0.75
     System
    0.74
     Company
    0.73
     Field
    0.72
    Activations Density 0.554%

    No Known Activations