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. 6047
    Prev
    Next
    INDEX
    Explanations

    attends to the token "should" from the token "you" to imply obligation or recommendation

    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
    0:0.07
    1:0.03
    2:0.03
    3:0.04
    4:0.05
    5:0.03
    6:0.06
    7:0.65
    Negative Logits
     myſelf
    -2.44
     Efq
    -2.39
     itſelf
    -2.34
     Monfieur
    -2.27
     Jefus
    -2.16
     Majefty
    -2.08
     purpoſe
    -2.08
     Anſ
    -2.06
     Theſe
    -2.06
     ſeveral
    -2.05
    POSITIVE LOGITS
     
    1.38
    ,
    1.16
     (
    1.16
     a
    1.05
    ↵
    1.05
     the
    1.05
     and
    1.03
     in
    1.03
     I
    1.02
    .
    1.01
    Activations Density 0.135%

    No Known Activations