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. 6933
    Prev
    Next
    INDEX
    Explanations

    attends to reference markers from various tokens throughout the text

    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
    1:0.13
    2:0.09
    3:0.09
    4:0.12
    5:0.15
    6:0.10
    7:0.19
    Negative Logits
     ModelExpression
    -0.32
    ]='\
    -0.30
     незавершена
    -0.29
    verzeichnis
    -0.26
     Conſ
    -0.26
     ویکی‌پدیای
    -0.26
    ONSORED
    -0.26
    __*/
    -0.25
    &&&&
    -0.25
    rrggbb
    -0.24
    POSITIVE LOGITS
     חיצוניים
    0.42
    Obrázky
    0.37
     cherchés
    0.33
    Дереккөздер
    0.32
    rungsseite
    0.31
    évaluateur
    0.30
    Билгалдахарш
    0.30
    tagHelperRunner
    0.30
    IContainer
    0.29
    bitset
    0.28
    Activations Density 0.003%

    No Known Activations