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. 6198
    Prev
    Next
    INDEX
    Explanations

    attends to hexadecimal tokens from other numbered tokens

    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
    0:0.09
    1:0.03
    2:0.02
    3:0.05
    4:0.08
    5:0.04
    6:0.05
    7:0.60
    Negative Logits
     la
    -0.27
     del
    -0.26
     $
    -0.26
     a
    -0.26
     "
    -0.26
     j
    -0.24
     h
    -0.24
     o
    -0.24
     et
    -0.24
     b
    -0.24
    POSITIVE LOGITS
     initComponents
    0.53
    PreferredItem
    0.52
    DoubleQuotes
    0.49
    RegressionTest
    0.48
     Monfieur
    0.47
     Theſe
    0.47
     Efq
    0.47
     itſelf
    0.44
     deſt
    0.44
     Diſ
    0.44
    Activations Density 0.258%

    No Known Activations