Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6366
    Prev
    Next
    INDEX
    Explanations

    attends to the token indicating a web link from the token indicating a reference or action to sign up

    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
    0:0.08
    1:0.14
    2:0.10
    3:0.10
    4:0.11
    5:0.05
    6:0.25
    7:0.14
    Negative Logits
     AssemblyProduct
    -0.48
     الحره
    -0.46
    toMatchSnapshot
    -0.45
    "}},
    -0.43
     propOrder
    -0.43
    queryInterface
    -0.41
    存于互联网档案馆
    -0.41
    ganu
    -0.41
    withIdentifier
    -0.41
    SequentialGroup
    -0.40
    POSITIVE LOGITS
     said
    0.23
    pae
    0.22
    “
    0.22
    昂
    0.21
    هم
    0.21
     ‘
    0.21
     “
    0.21
    geb
    0.20
    बा
    0.20
     Umständen
    0.20
    Activations Density 0.010%

    No Known Activations