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. 0-GEMMASCOPE-ATT-16K
    6. 6176
    Prev
    Next
    INDEX
    Explanations

    attends to the token "friendly" from various contexts of positive or accommodating interactions

    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
    0:0.59
    1:0.01
    2:0.02
    3:0.02
    4:0.21
    5:0.05
    6:0.01
    7:0.04
    Negative Logits
     I
    -0.35
     AspNetCore
    -0.33
     S
    -0.33
     and
    -0.33
     s
    -0.32
    <eos>
    -0.31
     T
    -0.30
    ,
    -0.29
     t
    -0.29
     ban
    -0.29
    POSITIVE LOGITS
    ніципалі
    0.51
     espagne
    0.51
     ſeveral
    0.49
     greateſt
    0.47
     Theſe
    0.46
     Diſ
    0.45
    Datuak
    0.45
     Houſe
    0.45
     espírito
    0.44
     purpoſe
    0.44
    Activations Density 0.013%

    No Known Activations