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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-ATT-16K
    6. 5654
    Prev
    Next
    INDEX
    Explanations

    attends to tokens that feature arithmetic operations or relations on both sides

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_10/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    0:0.13
    1:0.12
    2:0.11
    3:0.08
    4:0.05
    5:0.05
    6:0.05
    7:0.37
    Negative Logits
    AddTagHelper
    -0.41
    AndEndTag
    -0.36
     '\\;'
    -0.35
     OFDb
    -0.33
    PreferredItem
    -0.29
     beginnetje
    -0.29
    corazón
    -0.29
    〢
    -0.29
    ();)
    -0.28
     AppCompatTheme
    -0.28
    POSITIVE LOGITS
    出版年
    0.26
    putnik
    0.26
    maxcdn
    0.25
    чайно
    0.25
    дий
    0.25
    '
    0.25
    atoma
    0.24
     görüş
    0.24
    JoinTable
    0.24
    displayquote
    0.24
    Activations Density 0.696%

    No Known Activations