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. 6541
    Prev
    Next
    INDEX
    Explanations

    attends to the token "v" from variable-related 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
    0:0.07
    1:0.14
    2:0.05
    3:0.05
    4:0.16
    5:0.39
    6:0.04
    7:0.05
    Negative Logits
    
    -0.40
    InjectAttribute
    -0.34
     Tse
    -0.30
     colectiva
    -0.29
    |<\
    -0.29
    +:+
    -0.28
     OSP
    -0.28
    templateUrl
    -0.28
     Trotz
    -0.27
     Pilate
    -0.27
    POSITIVE LOGITS
     IV
    0.25
     tax
    0.24
     Tax
    0.24
     članak
    0.24
    logiques
    0.23
    logica
    0.23
    !*\
    0.22
    ciente
    0.22
    >");
    
    0.22
     proprement
    0.22
    Activations Density 0.030%

    No Known Activations