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. 6106
    Prev
    Next
    INDEX
    Explanations

    attends to the second token in the sequence from various occurrences of the initial token in the sequence

    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
    1:0.01
    2:0.04
    3:0.02
    4:0.16
    5:0.62
    6:0.03
    7:0.04
    Negative Logits
     sure
    -0.32
     thiệu
    -0.28
     anything
    -0.26
     reco
    -0.26
    ediat
    -0.25
    ComponentModel
    -0.25
     PropertyChanged
    -0.25
    пря
    -0.25
     Ku
    -0.25
     parti
    -0.25
    POSITIVE LOGITS
     tartalomajánló
    0.38
     contextLoads
    0.37
     تكبرها
    0.36
    GOTREF
    0.36
    MigrationBuilder
    0.36
     BoxFit
    0.36
    ^(@)
    0.36
     vectorielles
    0.35
     bénévoles
    0.34
     ouvertes
    0.34
    Activations Density 1.158%

    No Known Activations