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. 5597
    Prev
    Next
    INDEX
    Explanations

    attends to material-related tokens from associated plastic or metal tokens

    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
    0:0.05
    1:0.19
    2:0.06
    3:0.05
    4:0.18
    5:0.33
    6:0.05
    7:0.06
    Negative Logits
     handleMessage
    -0.26
     onAnimation
    -0.25
    ExtendWith
    -0.25
     dibat
    -0.25
     bandoulière
    -0.24
     Erl
    -0.24
     StringTokenizer
    -0.24
     balanceOf
    -0.24
    hold
    -0.24
     Pilgri
    -0.23
    POSITIVE LOGITS
    setVerticalGroup
    0.34
    roek
    0.33
    TintMode
    0.32
    ########.
    0.29
     laude
    0.28
    Ссылки
    0.28
    utory
    0.27
    loyds
    0.27
    )|^{
    0.26
     Drapeau
    0.26
    Activations Density 0.084%

    No Known Activations