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. 41
    Prev
    Next
    INDEX
    Explanations

    attends to the token "just" from various plain or straightforward tokens

    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
    0:0.04
    1:0.02
    2:0.03
    3:0.02
    4:0.74
    5:0.04
    6:0.03
    7:0.05
    Negative Logits
     AspNetCore
    -0.30
    tagHelperRunner
    -0.29
    TagHelper
    -0.28
     autorytatywna
    -0.27
    )(((
    -0.27
    änglich
    -0.27
    %");
    -0.27
     more
    -0.27
    tonsoft
    -0.25
    runOnUiThread
    -0.25
    POSITIVE LOGITS
     برانيه
    0.40
     ostavi
    0.38
     ویکی‌آمباردا
    0.36
     volete
    0.36
     opposites
    0.36
     MIPS
    0.34
    ChildScrollView
    0.34
     reprodução
    0.34
     Thea
    0.34
    WebServlet
    0.33
    Activations Density 0.343%

    No Known Activations