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. 1241
    Prev
    Next
    INDEX
    Explanations

    attends to tokens indicating "thereof" from tokens indicating "thereof."

    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
    1:0.05
    2:0.01
    3:0.07
    4:0.32
    5:0.15
    6:0.02
    7:0.02
    8:0.04
    9:0.02
    10:0.04
    11:0.04
    12:0.05
    13:0.02
    14:0.01
    15:0.02
    Negative Logits
    <unused43>
    -3.36
    <unused41>
    -3.36
    <pad>
    -3.34
    [@BOS@]
    -3.34
    <unused28>
    -3.34
    <unused42>
    -3.34
    <unused23>
    -3.34
    <unused14>
    -3.34
    <unused3>
    -3.34
    <unused8>
    -3.34
    POSITIVE LOGITS
     (
    1.50
     
    1.42
     and
    1.39
    ,
    1.38
    ↵↵
    1.36
     the
    1.33
    ↵
    1.32
    .
    1.31
     in
    1.28
     to
    1.27
    Activations Density 0.230%

    No Known Activations