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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6448
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    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
    -1.07
    一个
    -0.95
    ン
    -0.92
     Baldwin
    -0.84
    Barr
    -0.83
    oja
    -0.82
     Bartol
    -0.81
    ⁄
    -0.80
    н
    -0.80
    paya
    -0.78
    POSITIVE LOGITS
     Hennessy
    1.01
    ứt
    0.99
    ly
    0.93
    に
    0.92
     Lynd
    0.89
     يتيمه
    0.84
     Webber
    0.83
    adə
    0.83
    Michele
    0.82
     définiti
    0.81
    Activations Density 3.460%

    No Known Activations