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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6634
    Prev
    Next
    INDEX
    Explanations

    frequencies and durations related to time and schedules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hour
    -1.21
     Hour
    -1.13
    Hour
    -1.08
    hour
    -1.02
     HOUR
    -1.00
     Month
    -0.92
     month
    -0.89
    month
    -0.83
     hours
    -0.83
     Hours
    -0.82
    POSITIVE LOGITS
    ποίη
    0.49
    AndEndTag
    0.48
     verwijzen
    0.47
    neux
    0.47
    complexContent
    0.47
    ंदीखरीदारी
    0.46
    مقاله
    0.46
     bleek
    0.46
    ństwo
    0.44
    Normalization
    0.42
    Activations Density 0.100%

    No Known Activations