© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 13413
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms related to genetics and mutations

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

    Follows certain punctuation ("and", "Q:", ".")

    np_acts-logits-general · gemini-2.0-flash

    End is Centre Q Blog Antibody satisfies

    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
     disambiguazione
    -0.90
    Personendaten
    -0.89
     Forumite
    -0.74
    ghijkl
    -0.73
     "..\..\
    -0.73
     faſt
    -0.72
     betweenstory
    -0.72
    ſelf
    -0.71
     poffible
    -0.70
    المناصب
    -0.69
    POSITIVE LOGITS
     is
    1.16
     was
    0.74
     are
    0.72
     will
    0.66
     it
    0.65
     has
    0.63
     were
    0.62
     shall
    0.62
     isso
    0.61
     which
    0.60
    Activations Density 0.218%

    No Known Activations