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. 6575
    Prev
    Next
    INDEX
    Explanations

    attends to specific tokens that represent particular entities or concepts from their associated counterparts

    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
    0:0.06
    1:0.08
    2:0.05
    3:0.50
    4:0.08
    5:0.07
    6:0.05
    7:0.06
    Negative Logits
    errHandler
    -0.47
    AddTagHelper
    -0.46
    parseFrom
    -0.45
    noin
    -0.44
    zzleHttp
    -0.42
    });*/
    -0.40
    ]))
    
    -0.40
    '])){
    
    -0.40
     censi
    -0.40
    StoryboardSegue
    -0.40
    POSITIVE LOGITS
     LoggerFactory
    0.38
     creciendo
    0.37
    kannya
    0.35
     jį
    0.32
    batore
    0.31
    ژه
    0.31
     poils
    0.30
     toalha
    0.30
     tehd
    0.30
    ufig
    0.30
    Activations Density 0.480%

    No Known Activations