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-2-9B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 1307
    Prev
    Next
    INDEX
    Explanations

    attends to the character "@" from various tokens that are also preceded by this character

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-att/layer_0/width_16k/average_l0_61
    Prompts (Dashboard)
    16,384 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
    0:0.06
    1:0.03
    2:0.03
    3:0.04
    4:0.50
    5:0.05
    6:0.03
    7:0.02
    8:0.01
    9:0.02
    10:0.03
    11:0.02
    12:0.01
    13:0.02
    14:0.04
    15:0.02
    Negative Logits
     ​
    -0.90
     â
    -0.82
     
    -0.82
     
    -0.81
     @
    -0.81
     ‪
    -0.81
     �
    -0.79
     ``
    -0.78
     &#
    -0.78
     Â
    -0.77
    POSITIVE LOGITS
     vastaan
    0.93
     Infór
    0.91
     auroit
    0.90
     feroit
    0.88
     extranjera
    0.83
     prohibido
    0.81
     étoit
    0.81
     Económica
    0.80
     Inscrivez
    0.79
     aikaa
    0.79
    Activations Density 0.060%

    No Known Activations