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. 16-GEMMASCOPE-RES-16K
    6. 16023
    Prev
    Next
    INDEX
    Explanations

    specific genetic sequences and primer information related to PCR processes

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

    DNA primer sequences

    np_acts-logits-general · gemini-2.0-flash

    primers or oligonucleotide sequences

    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
     defaultstate
    -0.88
     تضيفلها
    -0.75
     дописавши
    -0.72
     Audiodateien
    -0.72
    setVerticalGroup
    -0.64
    Aiheesta
    -0.64
    клопе
    -0.63
    itology
    -0.61
    ankt
    -0.61
     @"/
    -0.61
    POSITIVE LOGITS
     âgées
    0.60
     Roskov
    0.56
    Hochspringen
    0.53
     foregoing
    0.51
     normaux
    0.51
     Seelen
    0.50
     argint
    0.49
     molars
    0.48
     germinate
    0.48
     Thebes
    0.48
    Activations Density 0.152%

    No Known Activations