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. 353
    Prev
    Next
    INDEX
    Explanations

    attends to the second data value marked as a single token from the first data value marked as a single token

    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
    0:0.15
    1:0.03
    2:0.07
    3:0.03
    4:0.52
    5:0.06
    6:0.04
    7:0.07
    Negative Logits
    ]),
    -0.43
    )],
    -0.42
     للاسماء
    -0.42
     }}"></
    -0.41
    ])+
    -0.41
    ']).
    -0.40
    ')],
    -0.40
    ]).
    -0.40
    enderror
    -0.40
    )"),
    -0.39
    POSITIVE LOGITS
     dichiarato
    0.39
     combs
    0.36
    Cyfeiriadau
    0.34
     Sigism
    0.34
     pulito
    0.34
     cappuccio
    0.34
     Armenians
    0.33
     trattato
    0.33
     maske
    0.33
     subtitle
    0.33
    Activations Density 0.004%

    No Known Activations