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. 6208
    Prev
    Next
    INDEX
    Explanations

    attends to verbs or actions from corresponding quoted statements

    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
    0:0.10
    1:0.19
    2:0.14
    3:0.10
    4:0.16
    5:0.09
    6:0.09
    7:0.09
    Negative Logits
     sanitaires
    -0.26
     Dokumentation
    -0.24
     Blessed
    -0.23
     [],
    
    -0.23
    Uris
    -0.23
     čier
    -0.22
     Raptor
    -0.22
     Reece
    -0.22
    apel
    -0.22
     blessed
    -0.22
    POSITIVE LOGITS
    intios
    0.44
    fjspx
    0.38
     препратки
    0.36
    GEBURTSDATUM
    0.35
    ########.
    0.35
     "..\..\
    0.35
     للاسماء
    0.34
    dafx
    0.34
     "..\..\..\
    0.34
    TypedDataSet
    0.34
    Activations Density 0.070%

    No Known Activations