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. 17
    Prev
    Next
    INDEX
    Explanations

    attends to the token "there" from tokens indicating existence or presence later in the sequence

    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
    0:0.05
    1:0.02
    2:0.02
    3:0.02
    4:0.11
    5:0.69
    6:0.02
    7:0.03
    Negative Logits
     بتاريخ
    -0.30
    anmoins
    -0.27
    Injectable
    -0.27
     and
    -0.25
     alapján
    -0.25
     Савезне
    -0.24
     pageContext
    -0.23
    ISODE
    -0.23
    endforeach
    -0.23
     dalamnya
    -0.23
    POSITIVE LOGITS
    GEBURTSDATUM
    0.60
    MigrationBuilder
    0.58
     cherchés
    0.58
    ⓧ
    0.56
     AssemblyProduct
    0.55
    ConstraintMaker
    0.53
    IndentedString
    0.50
     autorytatywna
    0.49
    oneofs
    0.47
    LookAnd
    0.46
    Activations Density 0.040%

    No Known Activations