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. 6049
    Prev
    Next
    INDEX
    Explanations

    attends to numerical tokens from unrelated tokens throughout the sequence

    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
    1:0.15
    2:0.06
    3:0.07
    4:0.06
    5:0.07
    6:0.49
    7:0.06
    Negative Logits
     or
    -0.35
    .
    -0.34
     the
    -0.33
     and
    -0.33
    </i>
    -0.32
     –
    -0.32
     so
    -0.32
    ,
    -0.31
    </em>
    -0.31
     “
    -0.31
    POSITIVE LOGITS
     مشين
    0.58
     defaultstate
    0.57
     cherchés
    0.55
    ⓧ
    0.51
     الرياضيه
    0.50
    @[+][
    0.49
    ImageContext
    0.49
     beginnetje
    0.49
     виправивши
    0.49
    setVerticalGroup
    0.48
    Activations Density 11.484%

    No Known Activations