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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5678
    Prev
    Next
    INDEX
    Explanations

    attends to a specified type or nature of a token from a broader category of tokens

    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
    0:0.09
    1:0.09
    2:0.08
    3:0.09
    4:0.08
    5:0.02
    6:0.14
    7:0.38
    Negative Logits
    VersionUID
    -0.35
    picasso
    -0.33
    DoubleQuotes
    -0.33
    ArrowToggle
    -0.32
    pidou
    -0.30
     bonfire
    -0.29
     maneuvers
    -0.29
     Samaria
    -0.29
    xffffffff
    -0.29
    WireFormat
    -0.29
    POSITIVE LOGITS
     présentes
    0.37
     незавершена
    0.33
     juridiques
    0.31
    Bronnen
    0.30
     doInBackground
    0.30
     présents
    0.30
     devenus
    0.30
     sauvages
    0.29
    uksi
    0.29
    
    
    0.29
    Activations Density 0.951%

    No Known Activations