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. 6386
    Prev
    Next
    INDEX
    Explanations

    attends to tokens marked with periods from tokens marked with commas

    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
    0:0.05
    1:0.05
    2:0.05
    3:0.05
    4:0.07
    5:0.62
    6:0.03
    7:0.04
    Negative Logits
     незавершена
    -0.34
     doubtnut
    -0.31
    covo
    -0.30
    bibinfo
    -0.29
     photolibrary
    -0.28
     perpetuity
    -0.28
    ENEFITS
    -0.28
    \]
    
    -0.28
     betweenstory
    -0.28
    uanya
    -0.28
    POSITIVE LOGITS
    MessageTagHelper
    0.23
    nocache
    0.23
    ism
    0.23
    typeorm
    0.21
    RegistryLite
    0.21
    v
    0.21
     Normdatei
    0.20
    ;
    0.20
    }{\
    0.20
    fr
    0.20
    Activations Density 0.397%

    No Known Activations