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. 18-GEMMASCOPE-RES-16K
    6. 3219
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to microscopy and imaging techniques

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

    Microscopy and microscope objectives

    np_acts-logits-general · gemini-2.0-flash

    microscope and microscopy terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpringBootTest
    -0.46
    ftagPool
    -0.46
    ۇ
    -0.46
     gril
    -0.45
     незавершена
    -0.45
    uera
    -0.44
     esti
    -0.42
    Sitemap
    -0.42
    Batter
    -0.42
    compute
    -0.42
    POSITIVE LOGITS
     microscope
    0.90
     Microscope
    0.84
    ########.
    0.81
    LookAnd
    0.77
     microscopy
    0.77
     nahilalakip
    0.75
     dives
    0.75
     viewing
    0.72
     magnification
    0.72
    MemoryWarning
    0.72
    Activations Density 0.920%

    No Known Activations