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. 10-GEMMASCOPE-ATT-16K
    6. 6077
    Prev
    Next
    INDEX
    Explanations

    attends to numbered references from subsequent citations

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_10/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    0:0.18
    1:0.23
    2:0.13
    3:0.09
    4:0.13
    5:0.06
    6:0.07
    7:0.08
    Negative Logits
     AssemblyTitle
    -0.48
    Tôi
    -0.35
    })));
    -0.35
    prefixer
    -0.34
    ież
    -0.34
    "]));
    -0.33
     AppCompatTheme
    -0.33
    inderella
    -0.32
    kuuta
    -0.31
     ")";
    -0.31
    POSITIVE LOGITS
     onAnimation
    0.36
    enderror
    0.34
     يتيمه
    0.33
    getMenuInflater
    0.32
    ExtendWith
    0.32
    ita
    0.29
     Suivez
    0.28
    icza
    0.28
    CodeDom
    0.28
    erialization
    0.28
    Activations Density 0.456%

    No Known Activations