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. 123
    Prev
    Next
    INDEX
    Explanations

    attends to the token "row" from various tokens that contain similar sounds or syllables within the context of different discussions

    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
    0:0.08
    1:0.02
    2:0.06
    3:0.04
    4:0.38
    5:0.24
    6:0.03
    7:0.11
    Negative Logits
     avoient
    -0.43
     Majefty
    -0.42
     exemplaires
    -0.40
     buone
    -0.40
     Efq
    -0.40
     âgé
    -0.39
     theſe
    -0.37
     poffible
    -0.37
     ſhe
    -0.36
     ſeveral
    -0.36
    POSITIVE LOGITS
    DockStyle
    0.56
    "]
    
    0.53
    "];
    
    0.49
    )";
    
    0.48
    "],
    
    0.47
    "):
    
    0.46
    PerformLayout
    0.46
     "");
    
    0.45
    ":
    
    0.45
     OFDb
    0.45
    Activations Density 0.047%

    No Known Activations