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. 6116
    Prev
    Next
    INDEX
    Explanations

    attends to numerical expressions marked with "@" from numerical values in brackets

    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
    0:0.12
    1:0.15
    2:0.13
    3:0.11
    4:0.12
    5:0.05
    6:0.11
    7:0.17
    Negative Logits
    httphttps
    -0.36
    bootstrapcdn
    -0.33
    marle
    -0.32
    észetes
    -0.32
    StoryboardSegue
    -0.31
     AssemblyCompany
    -0.31
     الحره
    -0.31
    adaptiveStyles
    -0.30
     typelib
    -0.30
    achella
    -0.30
    POSITIVE LOGITS
    IUrlHelper
    0.28
    keur
    0.26
    ук
    0.26
    que
    0.25
     complet
    0.24
     Behav
    0.24
    (",",
    0.24
    pern
    0.24
     $
    0.24
    ელი
    0.24
    Activations Density 0.043%

    No Known Activations