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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5551
    Prev
    Next
    INDEX
    Explanations

    attends to the token "m" from various coding-related tokens

    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
    0:0.57
    1:0.10
    2:0.06
    3:0.04
    4:0.04
    5:0.05
    6:0.04
    7:0.07
    Negative Logits
     opérés
    -0.30
     loro
    -0.29
    roda
    -0.28
     Persönlichkeit
    -0.28
     manuales
    -0.28
    外部リンク
    -0.27
    hão
    -0.27
    íncia
    -0.27
    createStatement
    -0.26
    wys
    -0.26
    POSITIVE LOGITS
     تضيفلها
    0.47
     autorytatywna
    0.46
     AssemblyCulture
    0.41
    Демографія
    0.40
    nodoc
    0.40
    Spoljašnje
    0.39
    pulumi
    0.39
    errHandler
    0.38
    elemField
    0.38
    sidemargin
    0.37
    Activations Density 0.307%

    No Known Activations