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. 5710
    Prev
    Next
    INDEX
    Explanations

    attends to terms related to specific concepts or objects from generally referenced terms

    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
    0:0.04
    1:0.10
    2:0.05
    3:0.03
    4:0.20
    5:0.46
    6:0.03
    7:0.04
    Negative Logits
     estekak
    -0.49
    Personensuche
    -0.40
    Personendaten
    -0.39
    تقاوى
    -0.37
     تضيفلها
    -0.35
     disponibilités
    -0.35
     Савезне
    -0.35
    DeleteBehavior
    -0.34
    UnusedPrivate
    -0.33
    #
    -0.32
    POSITIVE LOGITS
    </em>
    0.25
    Ac
    0.22
     Rudi
    0.22
     Frie
    0.21
     Lan
    0.21
    пт
    0.21
    agt
    0.21
    machi
    0.21
     mas
    0.21
    ult
    0.21
    Activations Density 0.521%

    No Known Activations