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. 1207
    Prev
    Next
    INDEX
    Explanations

    attends to specific terms or phrases when they are referenced or quoted from a later context, particularly focusing on a pattern involving desired tokens in a technical context

    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
    0:0.02
    1:0.01
    2:0.02
    3:0.03
    4:0.03
    5:0.02
    6:0.04
    7:0.03
    8:0.02
    9:0.02
    10:0.02
    11:0.03
    12:0.50
    13:0.07
    14:0.05
    15:0.02
    Negative Logits
    ,
    -1.36
     
    -1.13
     in
    -0.98
     and
    -0.93
    .
    -0.93
     of
    -0.91
     (
    -0.87
     to
    -0.84
     for
    -0.84
    ↵↵
    -0.83
    POSITIVE LOGITS
    <unused43>
    1.98
    <pad>
    1.98
    <unused41>
    1.98
    <unused74>
    1.98
    <unused51>
    1.97
    <unused42>
    1.97
    <unused23>
    1.97
    <unused14>
    1.96
    <unused3>
    1.96
    [@BOS@]
    1.96
    Activations Density 0.371%

    No Known Activations