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. 6064
    Prev
    Next
    INDEX
    Explanations

    attends to the tokens referring to "him" from tokens that refer back to the same entity

    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
    0:0.03
    1:0.64
    2:0.08
    3:0.02
    4:0.06
    5:0.06
    6:0.03
    7:0.04
    Negative Logits
     Савезне
    -0.74
    GEBURTSDATUM
    -0.74
    bootstrapcdn
    -0.70
     تضيفلها
    -0.69
    Vidite
    -0.68
    styleType
    -0.67
    Personensuche
    -0.67
    OGND
    -0.67
     disambiguazione
    -0.66
    awtextra
    -0.66
    POSITIVE LOGITS
     
    0.45
    ↵↵
    0.41
     (
    0.39
    The
    0.39
    (
    0.36
    y
    0.35
    <strong>
    0.34
    A
    0.34
    by
    0.34
    -
    0.34
    Activations Density 0.050%

    No Known Activations