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. 0-GEMMASCOPE-ATT-16K
    6. 193
    Prev
    Next
    INDEX
    Explanations

    attends to traffic-related tokens from tokens that follow, which are connected to the broader context of traffic systems, rules, and experiences

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.attn.hook_z
    Hook Layer
    0
    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
    0:0.55
    1:0.01
    2:0.03
    3:0.02
    4:0.21
    5:0.12
    6:0.01
    7:0.02
    Negative Logits
    CloseOperation
    -0.41
    racite
    -0.38
    falen
    -0.34
    featureID
    -0.34
    cellaneous
    -0.33
    uckleberry
    -0.33
    AddTagHelper
    -0.33
    씀
    -0.32
    รัฐ
    -0.32
    elry
    -0.31
    POSITIVE LOGITS
    tvguidetime
    0.63
    MENAFN
    0.40
    +#+#
    0.39
     CURLOPT
    0.38
     Besøkt
    0.37
    DrawerToggle
    0.37
     FetchType
    0.36
     normaux
    0.36
     initComponents
    0.36
    </tfoot>
    0.35
    Activations Density 0.007%

    No Known Activations