© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 6778
    Prev
    Next
    INDEX
    Explanations

    the term "special" and its variations, indicating a focus on exceptional or unique items and provisions

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

    "special" and following words

    np_acts-logits-general · gemini-2.0-flash

    special... context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mouseY
    -0.62
     Philist
    -0.62
     Humanos
    -0.56
     незавершена
    -0.56
    thmus
    -0.50
    CPtr
    -0.49
    batis
    -0.49
     decimos
    -0.48
     kaynağından
    -0.48
     Heels
    -0.48
    POSITIVE LOGITS
     special
    0.85
    SPECIAL
    0.84
     Special
    0.84
     SPECIAL
    0.78
    Special
    0.74
     purpose
    0.73
    special
    0.72
     speciale
    0.72
    Sonder
    0.71
     edition
    0.67
    Activations Density 0.151%

    No Known Activations