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. 10-GEMMASCOPE-ATT-16K
    6. 5830
    Prev
    Next
    INDEX
    Explanations

    attends to personal pronouns in the context of the advice or insights being given, suggesting a focus on individual experiences and perspectives

    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
    1:0.09
    2:0.07
    3:0.07
    4:0.06
    5:0.03
    6:0.20
    7:0.37
    Negative Logits
     createState
    -0.36
     للمعارف
    -0.24
    colgroup
    -0.24
    HasIndex
    -0.22
    SBATCH
    -0.21
    nesc
    -0.20
    ,
    -0.20
     духо
    -0.19
     причи
    -0.19
    ียน
    -0.19
    POSITIVE LOGITS
    Geplaatst
    0.42
     referenties
    0.41
     itſelf
    0.40
    ()?;
    0.39
    windowFixed
    0.38
     néglig
    0.37
     stessi
    0.36
     Cinema
    0.36
    </h4>
    0.36
    NotEqualTo
    0.36
    Activations Density 0.138%

    No Known Activations