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. 8-GEMMASCOPE-RES-16K
    6. 15130
    Prev
    Next
    INDEX
    Explanations

    specific scientific terms and variables related to chemical and physical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.51
     kasarigan
    -0.47
    بوابة
    -0.46
     mis
    -0.45
    ocal
    -0.41
     du
    -0.41
    SAMPLES
    -0.41
    мии
    -0.40
     SENS
    -0.40
     Ras
    -0.39
    POSITIVE LOGITS
    Obrázky
    0.72
     चीज़ों
    0.67
    NUMX
    0.66
     CJK
    0.65
     lenker
    0.64
    didSet
    0.63
     fufficient
    0.63
    BibitemShut
    0.63
     IndexError
    0.63
    verständlich
    0.63
    Activations Density 0.646%

    No Known Activations