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. 6484
    Prev
    Next
    INDEX
    Explanations

    attends to varying characteristics of game mechanics from costs associated with those mechanics

    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
    0:0.08
    1:0.10
    2:0.10
    3:0.12
    4:0.11
    5:0.06
    6:0.19
    7:0.19
    Negative Logits
     ogóle
    -0.36
    帖最后由
    -0.29
    ”
    -0.28
    dto
    -0.27
     kambing
    -0.26
     Venn
    -0.26
    Pan
    -0.26
    」
    -0.25
    “
    -0.25
    ?”
    -0.24
    POSITIVE LOGITS
    cifix
    0.42
    UnitTesting
    0.38
    ihnachten
    0.37
    WebControls
    0.37
    rrggbb
    0.37
    wnież
    0.36
    oudre
    0.36
    lotten
    0.35
    chedelic
    0.35
    出版年
    0.35
    Activations Density 0.106%

    No Known Activations