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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 0-GEMMASCOPE-ATT-16K
    6. 6084
    Prev
    Next
    INDEX
    Explanations

    attends to mathematical and programming tokens related to norms and transformations from operational symbols in a structured format

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.attn.hook_z
    Hook Layer
    0
    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
    0:0.02
    1:0.04
    2:0.04
    3:0.09
    4:0.07
    5:0.05
    6:0.60
    7:0.06
    Negative Logits
    LookAnd
    -1.19
     مشين
    -1.15
    "])
    
    -1.14
     estekak
    -1.14
     propOrder
    -1.13
     виправивши
    -1.13
    BeginContext
    -1.12
     @"/
    -1.11
    "]));
    -1.11
    DoubleQuotes
    -1.10
    POSITIVE LOGITS
    ,
    1.21
    ↵↵
    0.77
     
    0.68
    .
    0.62
    '
    0.61
    -
    0.60
     (
    0.60
    /
    0.58
    ;
    0.58
     and
    0.56
    Activations Density 0.005%

    No Known Activations