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. 360
    Prev
    Next
    INDEX
    Explanations

    attends to tokens related to "hyper" from tokens related to "hyper" across various contexts

    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
    1:0.73
    2:0.03
    3:0.02
    4:0.05
    5:0.04
    6:0.02
    7:0.03
    Negative Logits
     du
    -0.49
     co
    -0.47
     sub
    -0.47
     
    -0.47
     re
    -0.47
     anti
    -0.46
     f
    -0.44
     qu
    -0.44
     l
    -0.44
     p
    -0.44
    POSITIVE LOGITS
     Anſ
    0.83
     pleaſure
    0.82
     itſelf
    0.82
     ainfi
    0.82
     myſelf
    0.81
     Efq
    0.81
     Monfieur
    0.81
     houſe
    0.81
     Theſe
    0.79
     avoient
    0.79
    Activations Density 4.364%

    No Known Activations