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. 6041
    Prev
    Next
    INDEX
    Explanations

    attends to punctuation tokens from tokens related to variables or settings

    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
    0:0.05
    1:0.02
    2:0.02
    3:0.03
    4:0.72
    5:0.04
    6:0.06
    7:0.02
    Negative Logits
    \[
    -0.24
    i
    -0.24
     femmin
    -0.23
    dc
    -0.22
    Offer
    -0.22
     funghi
    -0.21
     psicológica
    -0.21
    $\
    -0.21
     Dott
    -0.21
    offer
    -0.21
    POSITIVE LOGITS
    ResumeLayout
    0.50
    WriteBarrier
    0.49
     snippetHide
    0.47
    archiviato
    0.45
     BorderRadius
    0.44
    zzleHttp
    0.44
     مرئيه
    0.43
    ChildScrollView
    0.43
     يتيمه
    0.43
    HasForeignKey
    0.42
    Activations Density 0.366%

    No Known Activations