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. 5933
    Prev
    Next
    INDEX
    Explanations

    attends to bean-related tokens from public access specifier 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
    0:0.08
    1:0.12
    2:0.11
    3:0.11
    4:0.10
    5:0.06
    6:0.17
    7:0.22
    Negative Logits
    脚注の使い方
    -0.54
     estekak
    -0.49
    AsUp
    -0.48
    XMLSchema
    -0.48
     незавершена
    -0.45
    UnusedPrivate
    -0.44
    ArrowToggle
    -0.44
    InjectAttribute
    -0.44
    TagMode
    -0.44
     disambiguazione
    -0.42
    POSITIVE LOGITS
     she
    0.27
     her
    0.23
     inti
    0.23
     he
    0.22
    !)
    0.22
    重点
    0.22
     when
    0.21
    >
    
    
    0.21
     our
    0.21
     so
    0.20
    Activations Density 0.016%

    No Known Activations