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. 6429
    Prev
    Next
    INDEX
    Explanations

    attends to tokens indicating the nature of functions or operations from tokens representing their parameters or functional 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
    0:0.15
    1:0.13
    2:0.11
    3:0.08
    4:0.06
    5:0.04
    6:0.07
    7:0.33
    Negative Logits
    VIAF
    -0.32
    withIdentifier
    -0.28
     VIAF
    -0.27
     known
    -0.26
    INDIC
    -0.25
    ius
    -0.25
     Met
    -0.25
    固
    -0.25
    沙
    -0.25
     As
    -0.24
    POSITIVE LOGITS
     defaultstate
    0.48
    setVerticalGroup
    0.40
     "..\..\..\
    0.37
    MessageOf
    0.37
    InjectAttribute
    0.37
    enderror
    0.36
     Normdatei
    0.35
     pleaſure
    0.35
    ьаж
    0.35
    UnsafeEnabled
    0.34
    Activations Density 0.068%

    No Known Activations