Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6156
    Prev
    Next
    INDEX
    Explanations

    attends to the specific zero time markers from another pair of later timestamped tokens

    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
    0:0.04
    1:0.08
    2:0.05
    3:0.22
    4:0.24
    5:0.09
    6:0.14
    7:0.09
    Negative Logits
    enschappe
    -0.32
    <eos>
    -0.30
    ↵↵
    -0.27
     Roskov
    -0.27
    に出
    -0.25
     fla
    -0.25
     div
    -0.24
     in
    -0.23
     $
    -0.23
    cshtml
    -0.23
    POSITIVE LOGITS
    expandindo
    0.52
    IntoConstraints
    0.51
     InputDecoration
    0.49
     eſt
    0.45
     Audiodateien
    0.43
     समीक्षाएं
    0.43
    principalColumn
    0.43
    RectangleBorder
    0.42
     ainfi
    0.42
    extAlignment
    0.42
    Activations Density 0.051%

    No Known Activations