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. 15-GEMMASCOPE-RES-16K
    6. 12800
    Prev
    Next
    INDEX
    Explanations

    phrases related to property interests and financial or legal processes

    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
     and
    -1.81
     or
    -1.25
     및
    -1.21
    および
    -1.10
    และ
    -1.07
     \&
    -1.04
     &
    -1.02
    性和
    -0.98
    及び
    -0.97
     и
    -0.94
    POSITIVE LOGITS
    Rujuakan
    0.54
    AdapterFactory
    0.51
    recated
    0.50
     verle
    0.49
    pannt
    0.49
     Whitaker
    0.49
     himo
    0.49
    USAL
    0.49
    calaure
    0.48
    angnya
    0.47
    Activations Density 1.968%

    No Known Activations