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. 1-GEMMASCOPE-RES-16K
    6. 7075
    Prev
    Next
    INDEX
    Explanations

    references to cultural customs and established practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -1.06
    Referanser
    -0.89
     oprot
    -0.78
    存于互联网档案馆
    -0.74
    EDEFAULT
    -0.71
    WithIOException
    -0.68
    nextProps
    -0.67
    writeFieldEnd
    -0.67
    aarrggbb
    -0.66
     beginnetje
    -0.66
    POSITIVE LOGITS
     Union
    0.76
     heritage
    0.70
    Union
    0.69
     traditions
    0.69
     tradition
    0.66
     Tradition
    0.62
     Traditions
    0.61
     convention
    0.56
     UNION
    0.55
    union
    0.55
    Activations Density 0.065%

    No Known Activations