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. 10-GEMMASCOPE-ATT-16K
    6. 6228
    Prev
    Next
    INDEX
    Explanations

    attends to affirmative statements from negative or neutral experiences

    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
    0:0.10
    1:0.14
    2:0.11
    3:0.12
    4:0.13
    5:0.02
    6:0.13
    7:0.20
    Negative Logits
    ordning
    -0.36
    vägen
    -0.32
     Farrar
    -0.31
    udadera
    -0.30
    Geschäfts
    -0.30
    valently
    -0.29
    monės
    -0.29
    lawesi
    -0.29
     Jurí
    -0.28
    isasi
    -0.28
    POSITIVE LOGITS
    ValueStyle
    0.45
    UnitTesting
    0.40
     متعلقه
    0.39
    ///</
    0.35
    PerformLayout
    0.34
     lenker
    0.33
    AntiForgeryToken
    0.33
     AssemblyTitle
    0.32
     Normdatei
    0.31
    setVerticalGroup
    0.31
    Activations Density 0.335%

    No Known Activations