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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15663
    Prev
    Next
    INDEX
    Explanations

    keywords related to brain function and neural health

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

    Brain regions and anatomical terms

    np_acts-logits-general · gemini-2.0-flash

    brain areas and nuclei

    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
    jning
    -0.57
     utafitiHapana
    -0.54
     وتسجيلات
    -0.51
     CanadaChoose
    -0.50
    formik
    -0.50
    CloseOperation
    -0.49
    pues
    -0.48
     Horizonte
    -0.47
    AccessorTable
    -0.45
    オープ
    -0.45
    POSITIVE LOGITS
     Brod
    0.73
    Bro
    0.64
     فريبيس
    0.64
     Bro
    0.63
     nucleus
    0.63
     insu
    0.60
     frontal
    0.60
     Bader
    0.58
    surate
    0.57
     areas
    0.57
    Activations Density 0.514%

    No Known Activations