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. 6535
    Prev
    Next
    INDEX
    Explanations

    attends to tokens marked by double quotes or certain symbols from tokens that contain complex coding structures or elements

    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
    1:0.10
    2:0.10
    3:0.12
    4:0.16
    5:0.08
    6:0.19
    7:0.13
    Negative Logits
    iastes
    -0.38
    poptosis
    -0.36
    ceuticals
    -0.35
     bezeichneter
    -0.34
    ceutical
    -0.34
    vastava
    -0.34
    ?}",
    -0.33
     MonoBehaviour
    -0.33
    InvalidProtocol
    -0.33
    sfw
    -0.33
    POSITIVE LOGITS
     leçons
    0.34
    Produzione
    0.34
     shur
    0.32
     ProtoMessage
    0.31
    Lähteet
    0.31
    الحياه
    0.31
     reç
    0.30
    DrawerToggle
    0.30
     bassin
    0.30
    ніципалі
    0.30
    Activations Density 0.033%

    No Known Activations