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. 199
    Prev
    Next
    INDEX
    Explanations

    attends to ambiguous tokens from context-specific tokens

    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
    0:0.01
    1:0.03
    2:0.03
    3:0.11
    4:0.11
    5:0.04
    6:0.55
    7:0.09
    Negative Logits
     CreateTagHelper
    -0.54
    Personensuche
    -0.44
    RenderAtEndOf
    -0.42
    Datuak
    -0.41
    FormTagHelper
    -0.40
     كومونز
    -0.40
    rungsseite
    -0.40
     utafitiHapana
    -0.39
    MemoryWarning
    -0.38
     iſt
    -0.37
    POSITIVE LOGITS
    ,
    0.32
    ↵
    0.29
     of
    0.28
    .
    0.27
    })).
    0.25
     .
    0.24
    Browsable
    0.24
    IMPORTED
    0.23
    </h1>
    0.23
    endforeach
    0.23
    Activations Density 0.185%

    No Known Activations