Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6461
    Prev
    Next
    INDEX
    Explanations

    attends to the reference to "Dudarova" from the mathematical expression involving "t" and its powers

    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
    0:0.09
    1:0.18
    2:0.13
    3:0.09
    4:0.14
    5:0.11
    6:0.10
    7:0.13
    Negative Logits
    stalgia
    -0.29
    yntaxException
    -0.29
    niająca
    -0.27
    MergeFrom
    -0.24
    unmodifiable
    -0.24
    >(_
    -0.24
    thâu
    -0.24
    roxene
    -0.24
    riors
    -0.23
    GEBURTS
    -0.23
    POSITIVE LOGITS
     NgModule
    0.35
    
    0.32
     समीक्षाओं
    0.32
    eace
    0.30
    
    0.30
     חיצוניים
    0.29
    oa̍t
    0.29
     Planta
    0.29
    viewDidLoad
    0.29
     fédé
    0.28
    Activations Density 0.004%

    No Known Activations