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. 372
    Prev
    Next
    INDEX
    Explanations

    attends to the word "actually" from another "actually" appearing later 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
    0:0.06
    1:0.46
    2:0.19
    3:0.03
    4:0.08
    5:0.04
    6:0.05
    7:0.05
    Negative Logits
     Shakspeare
    -0.44
     raiſ
    -0.41
     ſy
    -0.40
     Diſ
    -0.40
     whoſe
    -0.39
     myſelf
    -0.39
     purpoſe
    -0.39
     ſta
    -0.39
     themſelves
    -0.38
     Tacitus
    -0.38
    POSITIVE LOGITS
     propOrder
    0.51
    oredCriteria
    0.50
     Sch
    0.44
     disambiguazione
    0.44
     Mc
    0.41
    KURZBESCHREIBUNG
    0.41
     Bell
    0.40
    tagHelperRunner
    0.40
    memoized
    0.40
     الدولى
    0.39
    Activations Density 0.042%

    No Known Activations