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. 5810
    Prev
    Next
    INDEX
    Explanations

    attends to functions and methods marked by "void" from commands that involve specific actions, showing a focus on function declarations and calls within code

    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
    0:0.23
    1:0.14
    2:0.13
    3:0.04
    4:0.05
    5:0.04
    6:0.05
    7:0.27
    Negative Logits
     Curi
    -0.26
     montanha
    -0.26
    marvin
    -0.25
    Producción
    -0.25
    Gön
    -0.25
     Old
    -0.25
    norr
    -0.24
    NameIn
    -0.24
     отказа
    -0.24
    tyn
    -0.24
    POSITIVE LOGITS
    MessageOf
    0.50
    توض
    0.41
    DockStyle
    0.40
    Климат
    0.40
     kasarigan
    0.39
     tfsi
    0.39
     disambiguazione
    0.39
    Демографія
    0.38
    appé
    0.38
    EndContext
    0.36
    Activations Density 0.081%

    No Known Activations