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. 1237
    Prev
    Next
    INDEX
    Explanations

    attends to singular determiners or articles from conjunctions or plural determiners

    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
    0:0.08
    1:0.08
    2:0.03
    3:0.04
    4:0.06
    5:0.26
    6:0.03
    7:0.02
    8:0.04
    9:0.04
    10:0.04
    11:0.04
    12:0.07
    13:0.06
    14:0.03
    15:0.02
    Negative Logits
    ,
    -1.68
     
    -1.68
     (
    -1.63
    .
    -1.62
    ↵
    -1.56
    ↵↵
    -1.55
    -
    -1.55
    <eos>
    -1.42
    ’
    -1.41
     I
    -1.40
    POSITIVE LOGITS
     queſta
    2.89
     myſelf
    2.78
    <unused74>
    2.70
    [@BOS@]
    2.70
    <unused41>
    2.70
    <unused16>
    2.69
    <unused23>
    2.69
    <unused14>
    2.69
    <unused3>
    2.69
    <unused8>
    2.69
    Activations Density 0.011%

    No Known Activations