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. 5356
    Prev
    Next
    INDEX
    Explanations

    attends to punctuation marks surrounding quoted speech from tokens later in the sequence

    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
    0:0.06
    1:0.07
    2:0.06
    3:0.09
    4:0.07
    5:0.03
    6:0.46
    7:0.11
    Negative Logits
    MLLoader
    -0.52
     disponibilités
    -0.43
     initComponents
    -0.42
    MethodManager
    -0.42
    AddHtmlAttribute
    -0.41
    igshid
    -0.40
    achal
    -0.37
    CompleteListener
    -0.37
    AutoresizingMask
    -0.36
    BeginInit
    -0.35
    POSITIVE LOGITS
    Personendaten
    0.33
    matchCondition
    0.32
     droit
    0.28
     endfor
    0.27
    WARN
    0.27
    клопе
    0.26
     مشين
    0.26
     domani
    0.25
     chré
    0.25
     action
    0.25
    Activations Density 0.058%

    No Known Activations