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-2-2B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 241
    Prev
    Next
    INDEX
    Explanations

    attends to the token "everyday" from various contexts referencing different aspects of daily life

    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
    0:0.31
    1:0.02
    2:0.04
    3:0.02
    4:0.37
    5:0.14
    6:0.02
    7:0.05
    Negative Logits
    GEBURTSDATUM
    -0.48
    Autoritní
    -0.35
    zeiti
    -0.35
    UnsafeEnabled
    -0.35
     lenker
    -0.35
    zeitig
    -0.33
     other
    -0.33
     time
    -0.32
    tubes
    -0.32
    comple
    -0.31
    POSITIVE LOGITS
    WriteBarrier
    0.43
     mapStateToProps
    0.43
     onResponse
    0.42
    requireNonNull
    0.40
    Xna
    0.39
    openzeppelin
    0.38
     rabat
    0.37
    saraba
    0.37
    printStackTrace
    0.35
     firebaseConfig
    0.35
    Activations Density 0.005%

    No Known Activations