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. 35
    Prev
    Next
    INDEX
    Explanations

    attends to the token "Category" from various category tokens

    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
    0:0.02
    1:0.05
    2:0.43
    3:0.12
    4:0.06
    5:0.10
    6:0.08
    7:0.10
    Negative Logits
     the
    -0.82
     it
    -0.69
     a
    -0.68
     all
    -0.64
     an
    -0.59
     is
    -0.59
     
    -0.59
     in
    -0.58
     The
    -0.58
     or
    -0.58
    POSITIVE LOGITS
     Shakspeare
    0.99
     photolibrary
    0.96
     crdi
    0.93
     cdti
    0.91
    Personendaten
    0.91
    verwijspagina
    0.91
     tfsi
    0.89
     moschino
    0.88
     negroes
    0.88
     sherds
    0.88
    Activations Density 5.299%

    No Known Activations