© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 8296
    Prev
    Next
    INDEX
    Explanations

    technical specifications and numerical values related to products or technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otomatig
    -0.85
    SharedCtor
    -0.82
    InjectAttribute
    -0.76
     PyLong
    -0.75
    Portály
    -0.73
     '\\;'
    -0.72
     TextAppearance
    -0.72
     насељу
    -0.72
    хьтан
    -0.71
     propOrder
    -0.69
    POSITIVE LOGITS
    ‚¬
    0.66
    Enllaces
    0.58
    metra
    0.56
    ligente
    0.54
    存于互联网档案馆
    0.52
    cshtml
    0.52
    )’
    0.50
    </h3>
    0.50
     holding
    0.49
     bege
    0.49
    Activations Density 0.147%

    No Known Activations