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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 200
    Prev
    Next
    INDEX
    Explanations

    references to prestigious awards and rankings related to educational institutions

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

    Rankings or lists

    np_acts-logits-general · gemini-2.0-flash

    ranked or ranking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    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
    -0.72
    SequentialGroup
    -0.66
     Wikispecies
    -0.65
     оригіналу
    -0.62
    DoubleQuotes
    -0.61
     Vikipedi
    -0.60
    entingan
    -0.60
     consultato
    -0.59
     TextAppearance
    -0.56
     خارجية
    -0.56
    POSITIVE LOGITS
     ranking
    0.92
     rankings
    0.92
     ranked
    0.90
    ranked
    0.79
    rank
    0.73
    Ranked
    0.72
     ranks
    0.71
     rank
    0.71
    ranking
    0.70
     Ranked
    0.67
    Activations Density 0.188%

    No Known Activations