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. 341
    Prev
    Next
    INDEX
    Explanations

    attends to instances of "hash" from instances of "Hashashin."

    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
    0:0.04
    1:0.16
    2:0.12
    3:0.05
    4:0.27
    5:0.23
    6:0.03
    7:0.06
    Negative Logits
     the
    -0.38
    ↵↵
    -0.38
     
    -0.35
    <eos>
    -0.35
     and
    -0.34
    "
    -0.34
    err
    -0.34
    n
    -0.33
    r
    -0.32
     a
    -0.32
    POSITIVE LOGITS
     BoxDecoration
    0.80
     tartalomajánló
    0.80
    setVerticalGroup
    0.75
    Personensuche
    0.75
     NSCoder
    0.71
     تضيفلها
    0.70
    __':
    
    0.70
    RegressionTest
    0.70
    MigrationBuilder
    0.70
     GenerationType
    0.69
    Activations Density 0.017%

    No Known Activations