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. 25
    Prev
    Next
    INDEX
    Explanations

    attends to government-related tokens from other government-related 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
    0:0.04
    1:0.64
    2:0.05
    3:0.03
    4:0.06
    5:0.05
    6:0.04
    7:0.05
    Negative Logits
     Púb
    -0.33
     alemana
    -0.31
     propOrder
    -0.30
     Werke
    -0.29
     Técnica
    -0.28
     Euripides
    -0.27
    多
    -0.27
     Klon
    -0.26
     Bigg
    -0.26
     Thebes
    -0.26
    POSITIVE LOGITS
    uestions
    0.36
    duled
    0.35
    NUMX
    0.35
    etheless
    0.34
    الحياه
    0.34
    %");
    0.34
    ourced
    0.33
    mitive
    0.33
    REQUENCY
    0.32
    unately
    0.32
    Activations Density 0.047%

    No Known Activations