© 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. 1727
    Prev
    Next
    INDEX
    Explanations

    sections of text that contain significant medical or legal information

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

    Uncommon punctuation and symbols

    np_acts-logits-general · gemini-2.0-flash

    testimony, gender, 備份檔案

    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
    uxxxx
    -1.06
     nakalista
    -1.04
    "])
    -1.01
     bezeichneter
    -0.98
     NUKAT
    -0.96
    ########.
    -0.95
     Мексичка
    -0.95
    исленность
    -0.94
    pecially
    -0.92
     استنادى
    -0.92
    POSITIVE LOGITS
    L
    0.67
    ti
    0.65
    li
    0.62
    et
    0.60
    O
    0.60
    R
    0.60
    te
    0.59
    M
    0.58
    U
    0.58
    ia
    0.57
    Activations Density 0.039%

    No Known Activations