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. 10-GEMMASCOPE-ATT-16K
    6. 5540
    Prev
    Next
    INDEX
    Explanations

    attends to numbered references from citations appearing 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
    0:0.10
    1:0.13
    2:0.09
    3:0.11
    4:0.10
    5:0.10
    6:0.16
    7:0.18
    Negative Logits
     '\\;'
    -0.26
    obium
    -0.26
    тнес
    -0.23
    Образова
    -0.23
    iliares
    -0.23
    phylococcus
    -0.22
     VIAF
    -0.22
    ijnt
    -0.22
     goals
    -0.22
    alker
    -0.22
    POSITIVE LOGITS
    tagHelperRunner
    0.37
    GEBURTSDATUM
    0.36
    ----</
    0.35
     resourceCulture
    0.32
    发表于
    0.31
     MaterialApp
    0.30
    Paz
    0.30
     للمعارف
    0.28
     Palgrave
    0.28
    CodeAttribute
    0.28
    Activations Density 0.009%

    No Known Activations