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. 5929
    Prev
    Next
    INDEX
    Explanations

    attends to the access modifier "public" from various class definitions

    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
    0:0.19
    1:0.28
    2:0.08
    3:0.08
    4:0.09
    5:0.08
    6:0.06
    7:0.10
    Negative Logits
    rateful
    -0.36
    *********/
    -0.36
    kespeare
    -0.34
    ẨM
    -0.32
    alanta
    -0.31
     

    -0.31
    ActionTypes
    -0.30
    tocks
    -0.30
     Bader
    -0.30
     SMP
    -0.30
    POSITIVE LOGITS
    expandindo
    0.62
    ########.
    0.51
    Autoritní
    0.45
    
    0.41
     HasFactory
    0.41
     صوتيه
    0.38
     '\\;'
    0.38
     PARSER
    0.36
    Produzione
    0.36
    SharedDtor
    0.35
    Activations Density 0.016%

    No Known Activations