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. 21-GEMMASCOPE-RES-16K
    6. 15085
    Prev
    Next
    INDEX
    Explanations

    mentions of legal cases and court-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nantucket
    -0.64
    Brunswick
    -0.57
    +#+#
    -0.55
     VDC
    -0.54
     étions
    -0.53
     désolés
    -0.52
    anover
    -0.52
     sánh
    -0.51
    Życiorys
    -0.51
    xodo
    -0.51
    POSITIVE LOGITS
     Oklahoma
    1.52
    Oklahoma
    1.39
     Okla
    1.22
     OK
    1.17
     Ok
    1.07
     Tulsa
    1.03
    lahoma
    0.99
     Edmond
    0.98
    LAHOMA
    0.98
     ok
    0.94
    Activations Density 0.118%

    No Known Activations