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. 6043
    Prev
    Next
    INDEX
    Explanations

    attends to the word "there" from correlative instances of "out there"

    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
    0:0.07
    1:0.40
    2:0.17
    3:0.04
    4:0.11
    5:0.05
    6:0.06
    7:0.05
    Negative Logits
     Monfieur
    -0.66
     Houſe
    -0.65
     Anſ
    -0.62
     Majefty
    -0.62
     Reſ
    -0.59
     itſelf
    -0.57
     Efq
    -0.56
     pleaſure
    -0.55
     raiſ
    -0.54
     purpoſe
    -0.54
    POSITIVE LOGITS
     
    0.44
     grand
    0.36
    qrstuvwxyz
    0.35
     Grand
    0.35
     en
    0.34
    oredCriteria
    0.34
     les
    0.34
     (
    0.33
     font
    0.33
     la
    0.33
    Activations Density 0.243%

    No Known Activations