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. 5999
    Prev
    Next
    INDEX
    Explanations

    attends to the category token from various instances where it is referenced later in the text

    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
    1:0.11
    2:0.06
    3:0.05
    4:0.20
    5:0.42
    6:0.03
    7:0.05
    Negative Logits
    ChildScrollView
    -0.44
     समीक्षक
    -0.40
    LLocation
    -0.40
    CodeAttribute
    -0.38
     themſelves
    -0.38
     Signalez
    -0.36
    CodedInputStream
    -0.35
     myſelf
    -0.35
    InvalidProtocol
    -0.34
    RenderAtEndOf
    -0.34
    POSITIVE LOGITS
    GEBURTSDATUM
    0.31
    佗
    0.26
     voie
    0.26
    <h2>
    0.25
    RetentionPolicy
    0.25
     pinulongan
    0.25
     Christo
    0.25
    ComponentScan
    0.24
    ッパ
    0.24
    IsUnicode
    0.24
    Activations Density 4.094%

    No Known Activations