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. 1243
    Prev
    Next
    INDEX
    Explanations

    attends to code-related tokens from the token "user."

    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
    0:0.00
    1:0.00
    2:0.70
    3:0.01
    4:0.01
    5:0.00
    6:0.04
    7:0.02
    8:0.02
    9:0.00
    10:0.01
    11:0.01
    12:0.01
    13:0.01
    14:0.06
    15:0.02
    Negative Logits
    ſelf
    -0.66
     zijne
    -0.66
     パンチラ
    -0.66
    bildtitel
    -0.64
     Dieſe
    -0.64
    <unused43>
    -0.64
    <pad>
    -0.63
     dieſen
    -0.63
    <unused20>
    -0.62
    <unused23>
    -0.62
    POSITIVE LOGITS
     price
    0.40
     time
    0.40
     way
    0.39
     the
    0.39
     number
    0.38
     word
    0.38
     test
    0.38
     de
    0.37
     whole
    0.37
     first
    0.37
    Activations Density 0.023%

    No Known Activations