© 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. 4-GEMMASCOPE-RES-16K
    6. 507
    Prev
    Next
    INDEX
    Explanations

    instances of the word "at" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.88
    DoubleQuotes
    -0.82
     hii
    -0.78
     CCL
    -0.78
     ſy
    -0.77
     Juno
    -0.77
    Nemo
    -0.75
     DSS
    -0.75
     Olom
    -0.73
    derry
    -0.73
    POSITIVE LOGITS
     at
    2.02
     At
    1.68
    At
    1.48
     AT
    1.45
    at
    1.23
    CreatedAt
    1.00
     createdAt
    1.00
    Tại
    0.99
     tại
    0.99
     Atkinson
    0.98
    Activations Density 0.272%

    No Known Activations