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. 10-GEMMASCOPE-ATT-16K
    6. 5986
    Prev
    Next
    INDEX
    Explanations

    attends to tokens that indicate names or titles from the surrounding context or description related to various subjects

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_10/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    0:0.10
    1:0.11
    2:0.07
    3:0.06
    4:0.07
    5:0.02
    6:0.25
    7:0.28
    Negative Logits
     esigen
    -0.36
    jetunion
    -0.34
     cser
    -0.31
     ferien
    -0.31
    jęt
    -0.30
    erequisites
    -0.30
     Cymru
    -0.29
    >),
    -0.28
     Fon
    -0.28
    setIcon
    -0.28
    POSITIVE LOGITS
     AssemblyCulture
    0.53
     referenties
    0.50
    الإنجليزية
    0.48
    Искәрмәләр
    0.46
    Abitanti
    0.44
    ReusableCell
    0.43
    MessageOf
    0.42
    migrationBuilder
    0.39
    vacy
    0.39
    ]")]
    0.39
    Activations Density 0.218%

    No Known Activations