Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5525
    Prev
    Next
    INDEX
    Explanations

    attends to subjective feelings or states from descriptive tokens that introduce them

    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
    0:0.08
    1:0.09
    2:0.13
    3:0.10
    4:0.07
    5:0.02
    6:0.13
    7:0.34
    Negative Logits
    ormais
    -0.32
    כשיו
    -0.29
     officielle
    -0.29
    תם
    -0.28
    austin
    -0.27
    jacent
    -0.26
    ército
    -0.26
    jdt
    -0.26
     legale
    -0.26
     Desai
    -0.26
    POSITIVE LOGITS
    ')";
    0.41
    )*/
    0.39
    )");
    
    0.38
    ]";
    0.37
    )')
    0.36
    )');
    0.36
    ."</
    0.34
     Paglinawan
    0.34
    tagHelperRunner
    0.34
    Παραπομπές
    0.34
    Activations Density 1.110%

    No Known Activations