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. 5656
    Prev
    Next
    INDEX
    Explanations

    attends to phrases expressing passion or commitment to various goals or values from the tokens marking specific actions or outcomes

    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
    0:0.14
    1:0.16
    2:0.12
    3:0.06
    4:0.05
    5:0.02
    6:0.05
    7:0.37
    Negative Logits
     et
    -0.27
    stro
    -0.25
     us
    -0.25
    FieldDescriptor
    -0.24
     +
    -0.23
     im
    -0.23
     But
    -0.23
    +#+#
    -0.22
     onto
    -0.22
     but
    -0.22
    POSITIVE LOGITS
    
    0.39
     ISNI
    0.37
    $}}
    0.36
     Jefus
    0.36
     թվական
    0.36
     auffi
    0.35
     Theſe
    0.35
    ientras
    0.35
     leaſt
    0.35
     ligiloj
    0.34
    Activations Density 0.146%

    No Known Activations