© 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. 16-GEMMASCOPE-RES-16K
    11. 8609
    Prev
    Next
    INDEX
    Explanations

    words associated with places, particularly educational institutions, and names of locations

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

    Tokens before organizations or names

    np_acts-logits-general · gemini-2.0-flash

    Magdalen College, Landis+Gyr, tights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    й
    -1.15
    一个
    -0.94
    ン
    -0.93
    йки
    -0.92
    e
    -0.86
    н
    -0.83
    на
    -0.83
    м
    -0.79
    ים
    -0.78
    ه
    -0.75
    POSITIVE LOGITS
    に
    0.95
    ly
    0.94
     Lynd
    0.85
     suivie
    0.83
    hoeddwyd
    0.81
    ứt
    0.79
     Landis
    0.79
    bbene
    0.79
     Hennessy
    0.78
    ology
    0.78
    Activations Density 1.679%

    No Known Activations