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. 98
    Prev
    Next
    INDEX
    Explanations

    attends to recommendations from preceding phrases or clauses that provide explanations or instructions

    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
    0:0.65
    1:0.01
    2:0.01
    3:0.02
    4:0.18
    5:0.03
    6:0.02
    7:0.04
    Negative Logits
    U
    -0.30
     istor
    -0.29
    &#
    -0.28
    r
    -0.28
    of
    -0.28
    â
    -0.27
    cat
    -0.27
     =
    -0.27
     pavimento
    -0.27
    "/>
    -0.27
    POSITIVE LOGITS
    Portale
    0.46
    Искәрмәләр
    0.46
    はじめに
    0.45
    ConstraintMaker
    0.43
    jsxFileName
    0.43
    makeConstraints
    0.42
    FTFY
    0.42
    GTCX
    0.42
    migrationBuilder
    0.41
    QMetaType
    0.41
    Activations Density 0.025%

    No Known Activations