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. 5546
    Prev
    Next
    INDEX
    Explanations

    attends to specific segments of code or expressions that are indicated by pairs of asterisks from various other token types

    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
    1:0.16
    2:0.22
    3:0.12
    4:0.10
    5:0.05
    6:0.08
    7:0.13
    Negative Logits
    NameInMap
    -0.50
    IUrlHelper
    -0.48
     defStyleAttr
    -0.47
    lossians
    -0.44
    featureID
    -0.43
    ,:),
    -0.40
     BrowserModule
    -0.38
    */].
    -0.38
     دیکھیے
    -0.38
     Rptr
    -0.37
    POSITIVE LOGITS
     abband
    0.31
     giuri
    0.29
    شرة
    0.28
     tratti
    0.28
     Menlo
    0.28
     bebas
    0.27
     larga
    0.27
     faits
    0.27
    quate
    0.27
    ACIONAL
    0.27
    Activations Density 0.082%

    No Known Activations