© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 6880
    Prev
    Next
    INDEX
    Explanations

    unique identifiers, particularly names and numerical values associated with individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ably
    -0.88
    WebServlet
    -0.87
    Lindsey
    -0.85
    Ayo
    -0.83
     Folly
    -0.79
     STA
    -0.78
     Collin
    -0.78
    Georg
    -0.77
     Myrtle
    -0.77
    :][
    -0.76
    POSITIVE LOGITS
     Kew
    0.83
    Kew
    0.79
    렇
    0.74
    erton
    0.74
    sterone
    0.74
    ctile
    0.74
     Zidane
    0.72
     Barnes
    0.71
     Geng
    0.70
    NOWLEDG
    0.70
    Activations Density 2.059%

    No Known Activations