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. 6395
    Prev
    Next
    INDEX
    Explanations

    attends to sequences of characters or tokens from specific ending punctuation to opening brackets or brackets

    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
    2:0.08
    3:0.09
    4:0.15
    5:0.26
    6:0.06
    7:0.08
    Negative Logits
     quæ
    -0.37
    ſelf
    -0.32
    Datuak
    -0.32
     सत्यापित
    -0.30
     Guinée
    -0.30
     Monfieur
    -0.29
     giuri
    -0.29
     professionali
    -0.29
     vg
    -0.29
     houſe
    -0.29
    POSITIVE LOGITS
    SequentialGroup
    0.37
    chtenstein
    0.33
     Audiodateien
    0.32
    WriteAttribute
    0.28
     AssemblyProduct
    0.28
    }'.
    0.27
    +#+#
    0.26
     المعيارى
    0.26
    autoconfigure
    0.26
     Chwiliwch
    0.26
    Activations Density 0.039%

    No Known Activations