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

    Neuronpedia

    APICircuit 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. 0-GEMMASCOPE-ATT-16K
    6. 6026
    Prev
    Next
    INDEX
    Explanations

    attends to tokens related to debt from tokens discussing management or related concepts

    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
    0:0.56
    1:0.01
    2:0.04
    3:0.03
    4:0.21
    5:0.08
    6:0.01
    7:0.03
    Negative Logits
    CodeDom
    -0.26
    شهاد
    -0.25
    peutic
    -0.25
    .
    -0.23
    helial
    -0.23
    ↵↵
    -0.23
    jerc
    -0.23
     enforcement
    -0.23
     AppCompatTheme
    -0.23
     seem
    -0.22
    POSITIVE LOGITS
    ientôt
    0.43
    fromnode
    0.41
    Personendaten
    0.40
    GEBURTSDATUM
    0.39
    sizeCache
    0.39
     Theſe
    0.38
    ſtanding
    0.37
    gorithm
    0.37
     IBRARY
    0.36
    ADRID
    0.36
    Activations Density 0.007%

    No Known Activations