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

    Neuronpedia

    APICircuit 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. 6019
    Prev
    Next
    INDEX
    Explanations

    attends to tokens associated with objects or categories from related tokens that are active or have an action

    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
    0:0.39
    1:0.13
    2:0.07
    3:0.08
    4:0.08
    5:0.02
    6:0.08
    7:0.10
    Negative Logits
     is
    -0.33
    sig
    -0.28
     πλα
    -0.27
     করা
    -0.27
    is
    -0.27
     present
    -0.27
     république
    -0.27
     Nieren
    -0.26
    mera
    -0.26
    b
    -0.26
    POSITIVE LOGITS
    TagMode
    0.71
    SequentialGroup
    0.61
    Tikang
    0.57
    ArgsConstructor
    0.57
    Datuak
    0.54
    Personensuche
    0.52
    ChildScrollView
    0.52
    enumii
    0.52
    новниш
    0.51
    ConstraintMaker
    0.51
    Activations Density 6.903%

    No Known Activations