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. 6562
    Prev
    Next
    INDEX
    Explanations

    attends to numerical dimensions from instances of the last dimension

    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
    0:0.13
    1:0.14
    2:0.13
    3:0.09
    4:0.07
    5:0.06
    6:0.06
    7:0.28
    Negative Logits
     ['',
    -0.23
    lasser
    -0.22
    dónde
    -0.22
    AddTagHelper
    -0.22
    شهاد
    -0.21
    ParallelGroup
    -0.21
    ().__
    -0.21
    Find
    -0.21
    :✨
    -0.21
    ValueStyle
    -0.20
    POSITIVE LOGITS
    __*/
    0.33
    изнь
    0.29
    zzleHttp
    0.28
    rxjs
    0.28
     ddelweddau
    0.27
    yship
    0.27
     estimés
    0.27
    centers
    0.27
    astify
    0.26
     referenties
    0.26
    Activations Density 0.070%

    No Known Activations