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. 0-GEMMASCOPE-ATT-16K
    6. 340
    Prev
    Next
    INDEX
    Explanations

    attends from generic tokens related to dialogue or structure to specific numeric or scientific tokens mentioned later in the text

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.attn.hook_z
    Hook Layer
    0
    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
    0:0.03
    1:0.19
    2:0.08
    3:0.02
    4:0.05
    5:0.52
    6:0.03
    7:0.04
    Negative Logits
    ,’
    -0.55
    )’
    -0.54
    >');
    -0.53
    ),”
    -0.53
    '));
    
    -0.53
    '];
    
    -0.53
    ']);
    
    -0.53
    ');
    
    -0.53
    ),"
    -0.52
    '),
    
    -0.51
    POSITIVE LOGITS
     pleaſure
    0.49
     للمعارف
    0.49
    RetentionPolicy
    0.47
    OrNil
    0.47
     Monfieur
    0.46
    PerformLayout
    0.46
    Παραπομπές
    0.45
     &___
    0.45
     quæ
    0.44
     ejus
    0.44
    Activations Density 0.007%

    No Known Activations