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. 23
    Prev
    Next
    INDEX
    Explanations

    attends to the token "handset" from related telephone components

    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
    0:0.04
    1:0.75
    2:0.05
    3:0.01
    4:0.04
    5:0.04
    6:0.02
    7:0.02
    Negative Logits
    GraphicsUnit
    -0.37
     giudi
    -0.36
     giapp
    -0.35
     auroit
    -0.35
    FormTagHelper
    -0.35
     feroit
    -0.34
     ainfi
    -0.33
     spesa
    -0.32
     africains
    -0.31
     définiti
    -0.31
    POSITIVE LOGITS
     lenker
    0.29
    %");
    0.27
    WWWW
    0.27
    konferenz
    0.27
    "}";
    0.24
    oredCriteria
    0.24
    }}/>
    0.23
    ,:),
    0.23
     }}"></
    0.23
    °;
    0.23
    Activations Density 2.896%

    No Known Activations