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. 24-GEMMASCOPE-RES-16K
    6. 14619
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to specific diseases and their classifications

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

    Abbreviations or acronyms

    np_acts-logits-general · gemini-2.0-flash

    abbreviations and expanded forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DPS
    -0.74
     OGS
    -0.73
     SBC
    -0.73
     FES
    -0.72
     BPD
    -0.71
     BFS
    -0.71
     BCG
    -0.71
     SVD
    -0.70
     FSB
    -0.70
     BCC
    -0.69
    POSITIVE LOGITS
     kaarangay
    0.85
    Geplaatst
    0.81
    RenderAtEndOf
    0.79
     فريبيس
    0.79
     siglas
    0.78
     Chwiliwch
    0.75
     незавершена
    0.74
    stands
    0.73
     acronym
    0.72
    abestanden
    0.72
    Activations Density 0.693%

    No Known Activations