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. 6194
    Prev
    Next
    INDEX
    Explanations

    attends to the second numeric token from numeric tokens further 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
    0:0.08
    1:0.03
    2:0.04
    3:0.05
    4:0.06
    5:0.04
    6:0.10
    7:0.58
    Negative Logits
     Shakspeare
    -0.35
    MemoryWarning
    -0.34
    bootstrapcdn
    -0.34
     Pili
    -0.33
     cupola
    -0.33
    titure
    -0.33
     baf
    -0.31
    Geplaatst
    -0.31
    íncia
    -0.31
    KURZBESCHREIBUNG
    -0.30
    POSITIVE LOGITS
    ///</
    0.33
     esprits
    0.32
     pensées
    0.31
    Rigidbody
    0.29
     prêtres
    0.28
     Suppose
    0.27
    renia
    0.26
     réinitial
    0.26
     nemico
    0.26
    ⊤
    0.26
    Activations Density 0.511%

    No Known Activations