Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5747
    Prev
    Next
    INDEX
    Explanations

    attends to configuration-related tokens from tokens indicating file or stylistic elements

    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
    1:0.16
    2:0.10
    3:0.11
    4:0.20
    5:0.04
    6:0.11
    7:0.12
    Negative Logits
     snippetHide
    -0.67
    RenderAtEndOf
    -0.64
     '\\;'
    -0.57
     typelib
    -0.53
     NSCoder
    -0.52
    mybatisplus
    -0.50
    AddTagHelper
    -0.50
     الحره
    -0.49
     ISNI
    -0.49
    AndroidJUnit
    -0.49
    POSITIVE LOGITS
    aka
    0.32
    anda
    0.29
    de
    0.29
    last
    0.28
    dia
    0.28
     
    0.28
    л
    0.28
    ones
    0.27
    ma
    0.27
    holl
    0.27
    Activations Density 0.000%

    No Known Activations