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. 17-GEMMASCOPE-RES-16K
    6. 11318
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming errors and exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.83
    setViewportView
    -0.82
     useRouter
    -0.71
    verket
    -0.70
     vorn
    -0.69
    Marlene
    -0.69
    ibatis
    -0.69
    rgba
    -0.67
    icolor
    -0.67
    duğu
    -0.64
    POSITIVE LOGITS
     Exception
    0.79
    Exception
    0.72
    EXCEPTION
    0.69
     exemption
    0.69
     SSE
    0.65
     Kenner
    0.64
     exception
    0.62
     exciter
    0.62
     Jérôme
    0.59
    SSE
    0.59
    Activations Density 0.044%

    No Known Activations