© 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. 1-GEMMASCOPE-RES-16K
    6. 13192
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "examination" 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 @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LEGEND
    -0.65
    printLine
    -0.63
    legend
    -0.59
     Brust
    -0.59
     Vogt
    -0.58
    宜
    -0.56
    лару
    -0.55
    谣
    -0.54
    libft
    -0.54
     defaultstate
    -0.53
    POSITIVE LOGITS
     examination
    2.95
     Examination
    2.86
     examine
    2.80
    Examination
    2.72
     examined
    2.71
    examination
    2.63
     Examine
    2.59
     examining
    2.57
     examinations
    2.50
     EXAMINATION
    2.50
    Activations Density 0.099%

    No Known Activations