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. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 6134
    Prev
    Next
    INDEX
    Explanations

    attends to the token "require" from related Ruby code tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.attn.hook_z
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.05
    2:0.07
    3:0.07
    4:0.11
    5:0.04
    6:0.14
    7:0.47
    Negative Logits
    AndEndTag
    -0.41
     plagio
    -0.40
     itſelf
    -0.39
     Jefus
    -0.37
     Anger
    -0.37
     Influences
    -0.37
     pleaſure
    -0.37
     themſelves
    -0.37
     himſelf
    -0.36
    LookAnd
    -0.36
    POSITIVE LOGITS
    Билгалдахарш
    0.37
    
    0.33
     Wikimedijinoj
    0.31
    hoedd
    0.31
    ništ
    0.30
     Walkover
    0.29
    szön
    0.29
    Външни
    0.28
    orned
    0.28
     poveznice
    0.28
    Activations Density 0.371%

    No Known Activations