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. 10-GEMMASCOPE-ATT-16K
    6. 6251
    Prev
    Next
    INDEX
    Explanations

    attends to negative symbols from tokens involving rotational transformations

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_10/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    0:0.11
    1:0.14
    2:0.13
    3:0.16
    4:0.12
    5:0.06
    6:0.09
    7:0.15
    Negative Logits
    &\
    -0.20
     lom
    -0.19
    пуль
    -0.19
     fir
    -0.19
     Pul
    -0.19
     피
    -0.18
    اج
    -0.18
     viv
    -0.18
    xfe
    -0.18
    Ephe
    -0.18
    POSITIVE LOGITS
     Jefus
    0.44
     myſelf
    0.44
     purpoſe
    0.42
     Majefty
    0.42
     Chriftian
    0.41
     itſelf
    0.40
     supérieurs
    0.40
     Diſ
    0.40
     Anſ
    0.40
     Theſe
    0.39
    Activations Density 0.485%

    No Known Activations