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. 6041
    Prev
    Next
    INDEX
    Explanations

    attends to the token "to" from various following tokens

    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
    0:0.11
    1:0.12
    2:0.07
    3:0.05
    4:0.03
    5:0.02
    6:0.05
    7:0.51
    Negative Logits
     isComment
    -0.40
    =$?
    -0.37
     getItemCount
    -0.36
    StructEnd
    -0.35
    '},
    
    -0.33
     CreateTagHelper
    -0.33
    setContentView
    -0.31
    ^(@)
    -0.30
    '}>
    -0.30
    FormState
    -0.30
    POSITIVE LOGITS
     religieuses
    0.35
     "..\..\
    0.35
     hâte
    0.32
     "..\..\..\
    0.32
     intptr
    0.31
    visiae
    0.31
     Byers
    0.31
    றி
    0.30
     judicia
    0.29
     Vikipedi
    0.29
    Activations Density 0.462%

    No Known Activations