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. 5905
    Prev
    Next
    INDEX
    Explanations

    attends to the token "res" from numerical or programming-related 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
    0:0.14
    1:0.14
    2:0.11
    3:0.08
    4:0.07
    5:0.03
    6:0.07
    7:0.32
    Negative Logits
     EconPapers
    -0.46
    contentLoaded
    -0.44
    Autoritní
    -0.40
    DockStyle
    -0.40
    WriteBarrier
    -0.40
    ngdoc
    -0.39
    rungsseite
    -0.38
     ProtoMessage
    -0.37
    AddTagHelper
    -0.36
     <<<<<<<<<<<<<<
    -0.36
    POSITIVE LOGITS
      (
    0.30
     mã
    0.30
    ohjel
    0.28
     tasar
    0.28
    gew
    0.26
     Stories
    0.26
     filma
    0.26
    zeitige
    0.26
    สือ
    0.26
     Ciné
    0.25
    Activations Density 0.159%

    No Known Activations