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. 6152
    Prev
    Next
    INDEX
    Explanations

    attends to the token "In addition" from various subsequent tokens that expand on or elaborate ideas presented earlier in the text

    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
    0:0.06
    1:0.03
    2:0.04
    3:0.03
    4:0.63
    5:0.08
    6:0.04
    7:0.05
    Negative Logits
     iconFacebook
    -0.27
     it
    -0.27
     in
    -0.27
    だそうです
    -0.25
     the
    -0.25
     legyen
    -0.24
    doPost
    -0.24
     those
    -0.24
     which
    -0.23
     dalamnya
    -0.23
    POSITIVE LOGITS
    endpush
    0.47
    Geplaatst
    0.43
    Personensuche
    0.43
     referenties
    0.43
    ChildScrollView
    0.42
    __*/
    0.41
    IntoConstraints
    0.41
     cherchés
    0.40
    RegressionTest
    0.40
    ########.
    0.39
    Activations Density 1.648%

    No Known Activations