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. 6007
    Prev
    Next
    INDEX
    Explanations

    attends to code identifiers or data types from programming constructs or conditions within 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
    0:0.19
    1:0.22
    2:0.14
    3:0.08
    4:0.09
    5:0.05
    6:0.06
    7:0.13
    Negative Logits
    expandindo
    -0.64
    SharedDtor
    -0.58
    Personendaten
    -0.54
    ThroughAttribute
    -0.54
    gridx
    -0.53
    
    -0.52
     HttpNotFound
    -0.50
     betweenstory
    -0.49
    EDEFAULT
    -0.48
     useAppContext
    -0.48
    POSITIVE LOGITS
    部
    0.28
    ​
    0.26
    oso
    0.25
     lieb
    0.25
                    
    0.25
    月
    0.25
    bardziej
    0.25
    WriteLiteral
    0.25
    INF
    0.24
    dorf
    0.24
    Activations Density 16.634%

    No Known Activations