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-2-9B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 1201
    Prev
    Next
    INDEX
    Explanations

    attends to the dual slash from various segments within the sequences

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-att/layer_0/width_16k/average_l0_61
    Prompts (Dashboard)
    16,384 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
    0:0.03
    1:0.02
    2:0.00
    3:0.03
    4:0.01
    5:0.02
    6:0.32
    7:0.15
    8:0.02
    9:0.06
    10:0.04
    11:0.02
    12:0.02
    13:0.04
    14:0.08
    15:0.06
    Negative Logits
    <eos>
    -0.56
    0
    -0.52
     \
    -0.51
    /
    -0.49
     /
    -0.47
    3
    -0.45
    2
    -0.41
    \
    -0.41
    1
    -0.40
    {
    -0.39
    POSITIVE LOGITS
    <unused79>
    0.88
    <unused41>
    0.88
    <unused16>
    0.88
    [@BOS@]
    0.88
    <unused42>
    0.88
    <unused43>
    0.88
    <unused51>
    0.87
    <unused74>
    0.87
    <unused23>
    0.87
    <pad>
    0.87
    Activations Density 0.085%

    No Known Activations