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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-GEMMASCOPE-RES-16K
    6. 14893
    Prev
    Next
    INDEX
    Explanations

    terms related to imaging techniques and phenomena in materials science

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ymce
    -0.51
     doulou
    -0.50
    }{|
    -0.50
     vPvB
    -0.49
     ieee
    -0.49
     orec
    -0.48
    madas
    -0.48
     démocr
    -0.47
    carrier
    -0.47
     BorderRadius
    -0.47
    POSITIVE LOGITS
     poop
    0.72
    SpringRunner
    0.71
     microscope
    0.68
    Билгалдахарш
    0.68
     Microscopy
    0.66
     microscopy
    0.64
     confound
    0.63
     autopsy
    0.62
     swap
    0.62
     urine
    0.61
    Activations Density 2.617%

    No Known Activations