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. 6083
    Prev
    Next
    INDEX
    Explanations

    attends to types of real estate or property-related tokens from various general or descriptive 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
    0:0.10
    1:0.12
    2:0.09
    3:0.07
    4:0.08
    5:0.04
    6:0.14
    7:0.33
    Negative Logits
    évaluateur
    -0.37
     esternos
    -0.36
    AndEndTag
    -0.34
    UserScript
    -0.33
     initComponents
    -0.33
     betweenstory
    -0.33
    最快更新
    -0.32
    ContentAsync
    -0.31
    ergies
    -0.31
     utafitiHapana
    -0.31
    POSITIVE LOGITS
    writerow
    0.23
    sizeCache
    0.23
    statin
    0.23
    entrySet
    0.23
    いずれ
    0.22
    javax
    0.22
    PointerException
    0.22
    辐
    0.22
    าย
    0.22
    rát
    0.22
    Activations Density 0.053%

    No Known Activations