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-2-9B
    4. Attention Out - 16k
    5. 0-GEMMASCOPE-ATT-16K
    6. 1280
    Prev
    Next
    INDEX
    Explanations

    attends to the token "person" from related tokens "person."

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-att/layer_0/width_16k/average_l0_61
    Prompts (Dashboard)
    16,384 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
    0:0.04
    1:0.04
    2:0.01
    3:0.10
    4:0.41
    5:0.03
    6:0.04
    7:0.04
    8:0.01
    9:0.01
    10:0.03
    11:0.03
    12:0.09
    13:0.03
    14:0.01
    15:0.01
    Negative Logits
     juſ
    -0.30
     purpoſe
    -0.29
     pleaſure
    -0.28
     person
    -0.27
     perſon
    -0.27
     preſent
    -0.27
     enfans
    -0.26
     Verſ
    -0.26
     ſch
    -0.26
     Reſ
    -0.25
    POSITIVE LOGITS
     ")");
    0.47
     <<<<<<<<<<<<<<
    0.45
    )]
    
    0.42
    ")));
    
    0.42
    ]</
    0.42
    ).</
    0.41
    "])
    
    0.41
    ")]
    
    0.40
    ])),
    0.40
    ."),
    0.40
    Activations Density 0.027%

    No Known Activations