© 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. 7-GEMMASCOPE-RES-16K
    11. 9302
    Prev
    Next
    INDEX
    Explanations

    programming-related terms, particularly those associated with JSON and XML processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ThemeData
    -0.76
    SequentialGroup
    -0.74
     escra
    -0.69
     Burnt
    -0.67
     pornography
    -0.67
    ggak
    -0.66
    Mons
    -0.66
    Knock
    -0.66
     Iggy
    -0.65
    setHorizontal
    -0.65
    POSITIVE LOGITS
     Reader
    1.51
    Reader
    1.43
     reader
    1.38
    reader
    1.33
     READER
    1.20
     readers
    1.15
     Readers
    1.14
    Readers
    0.99
    readers
    0.92
    NewReader
    0.86
    Activations Density 0.066%

    No Known Activations