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. 5721
    Prev
    Next
    INDEX
    Explanations

    attends to various action verbs from elements specifying the object of consideration

    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
    0:0.22
    1:0.27
    2:0.08
    3:0.06
    4:0.06
    5:0.03
    6:0.04
    7:0.20
    Negative Logits
     Ing
    -0.23
    r
    -0.23
    ekyll
    -0.23
    RegistryLite
    -0.21
     Zacks
    -0.21
    わ
    -0.21
    시
    -0.21
    ㅐ
    -0.21
    了
    -0.21
    エール
    -0.21
    POSITIVE LOGITS
    Tikang
    0.50
     للمعارف
    0.47
    #+#
    0.45
    IUrlHelper
    0.45
    ScopeManager
    0.44
    TemporalType
    0.43
    ^(@)
    0.42
    webElementXpaths
    0.40
     صوتيه
    0.40
    
    0.40
    Activations Density 0.608%

    No Known Activations