Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 339
    Prev
    Next
    INDEX
    Explanations

    attends to names or proper nouns from subsequent punctuation or special characters

    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
    0:0.01
    1:0.04
    2:0.04
    3:0.57
    4:0.05
    5:0.04
    6:0.12
    7:0.08
    Negative Logits
    ,
    -0.54
    </i>
    -0.50
    ?
    -0.48
     (
    -0.48
     and
    -0.46
    ’
    -0.45
     the
    -0.43
    .
    -0.41
     W
    -0.40
     to
    -0.40
    POSITIVE LOGITS
     Meksiku
    0.76
     ſind
    0.71
     itſelf
    0.69
     ―――――
    0.68
     Efq
    0.66
    "):
    
    0.66
     myſelf
    0.66
     iſt
    0.65
     Theſe
    0.65
    "])
    
    0.65
    Activations Density 6.429%

    No Known Activations