Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6835
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical data related to percentages

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

    Percentages

    np_acts-logits-general · gemini-2.0-flash

    percentage representation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.55
     précie
    -0.54
    Ș
    -0.51
    ⟭
    -0.51
    paravant
    -0.51
    boucles
    -0.50
     Ewig
    -0.50
    ‌ی
    -0.48
    akaian
    -0.47
    galax
    -0.46
    POSITIVE LOGITS
     percent
    1.14
    percent
    0.92
     Percent
    0.87
     cent
    0.72
    Percent
    0.70
    новниш
    0.60
     Prozent
    0.57
     CURIAM
    0.56
     ciento
    0.55
     प्रतिशत
    0.55
    Activations Density 0.067%

    No Known Activations