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. 90
    Prev
    Next
    INDEX
    Explanations

    attends to generic tokens and specific tokens indicating types of animals or biological effects

    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
    0:0.01
    1:0.05
    2:0.07
    3:0.03
    4:0.03
    5:0.73
    6:0.04
    7:0.01
    Negative Logits
    BagConstraints
    -0.51
    endphp
    -0.45
    ptonshire
    -0.41
    endpush
    -0.39
    crollView
    -0.38
    ˏ
    -0.38
     odkazy
    -0.38
    MethodImpl
    -0.37
     nakalista
    -0.37
     שוליים
    -0.37
    POSITIVE LOGITS
     religieuses
    0.38
     marins
    0.35
    "
    0.35
    (
    0.34
    <td>
    0.34
     Italij
    0.33
    「
    0.33
    ?
    0.32
    RegressionTest
    0.32
     sposa
    0.32
    Activations Density 0.561%

    No Known Activations