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. 5925
    Prev
    Next
    INDEX
    Explanations

    attends to the token "exclusion" from the punctuation preceding it

    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
    0:0.42
    1:0.17
    2:0.13
    3:0.06
    4:0.07
    5:0.02
    6:0.05
    7:0.06
    Negative Logits
     semblables
    -0.19
    帖最后由
    -0.18
    chengladbach
    -0.17
     stanga
    -0.17
    prnewswire
    -0.16
    velocityY
    -0.16
    tagHelperRunner
    -0.16
     zusammenge
    -0.16
     avanti
    -0.15
     jaunes
    -0.15
    POSITIVE LOGITS
     propOrder
    0.36
    ]--;
    0.30
     '{@
    0.30
    VIAF
    0.29
    IBAction
    0.29
    pyplot
    0.28
     ),
    
    0.28
    GeoNames
    0.28
    CrossRef
    0.27
    "],
    
    0.27
    Activations Density 0.801%

    No Known Activations