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. 0-GEMMASCOPE-ATT-16K
    6. 191
    Prev
    Next
    INDEX
    Explanations

    attends to the term "included" from various subsequent tokens, often related to lists or collections of items or features

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.attn.hook_z
    Hook Layer
    0
    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
    0:0.56
    1:0.01
    2:0.01
    3:0.01
    4:0.28
    5:0.02
    6:0.01
    7:0.06
    Negative Logits
    GraphicsUnit
    -0.52
    XmlAccessType
    -0.51
    ")));
    
    -0.47
    ⁩
    -0.45
     ProtoMessage
    -0.45
    posedge
    -0.44
    Архівовано
    -0.44
    nambuco
    -0.44
    UAGE
    -0.44
    Πηγή
    -0.43
    POSITIVE LOGITS
    at
    0.34
    I
    0.33
    al
    0.33
    L
    0.32
    ac
    0.31
    one
    0.31
     riuscito
    0.31
    B
    0.31
    b
    0.31
    na
    0.31
    Activations Density 0.040%

    No Known Activations