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. 291
    Prev
    Next
    INDEX
    Explanations

    attends to "door" from various contexts where entries or exits are discussed

    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
    0:0.71
    1:0.03
    2:0.01
    3:0.02
    4:0.11
    5:0.04
    6:0.01
    7:0.03
    Negative Logits
     poveznice
    -0.31
     linkovi
    -0.28
     ivelany
    -0.28
     kasarigan
    -0.27
     HttpNotFound
    -0.26
    Bibliograf
    -0.26
    الإنجليزية
    -0.26
    ]--;
    -0.26
    Билгалдахарш
    -0.25
     shorthand
    -0.25
    POSITIVE LOGITS
     iconTwitter
    0.33
     esist
    0.33
    ншни
    0.31
     FetchType
    0.31
    queryInterface
    0.30
    VIAF
    0.30
    ſelves
    0.30
     InputDecoration
    0.30
    soever
    0.29
    gameserver
    0.29
    Activations Density 0.005%

    No Known Activations