© 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. 12598
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of published articles and their details

    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
    Cubit
    -0.47
    lolo
    -0.41
    Przypisy
    -0.39
     wechseln
    -0.39
     linkovi
    -0.38
    Unmarshaller
    -0.38
    previous
    -0.38
    almost
    -0.37
     nesten
    -0.37
     letzten
    -0.36
    POSITIVE LOGITS
     fuller
    1.37
     full
    1.11
     deeper
    1.10
     further
    1.07
     formal
    1.01
    full
    0.98
    正式
    0.98
    Full
    0.96
    เต็ม
    0.96
     formally
    0.95
    Activations Density 0.576%

    No Known Activations