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. 10-GEMMASCOPE-ATT-16K
    6. 5383
    Prev
    Next
    INDEX
    Explanations

    attends to numerical indicators and specific edition or version tokens from subsequent references

    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
    0:0.13
    1:0.23
    2:0.15
    3:0.08
    4:0.08
    5:0.03
    6:0.05
    7:0.20
    Negative Logits
    TestingModule
    -0.29
    ariam
    -0.23
    ʁ
    -0.22
    编
    -0.21
     fram
    -0.21
     inferior
    -0.21
    ']==
    -0.21
     Chau
    -0.21
     Amor
    -0.21
    Flat
    -0.21
    POSITIVE LOGITS
    يكب
    0.46
    +#+#
    0.45
    TRIBUN
    0.39
    expandindo
    0.39
     متعلقه
    0.37
     Italijani
    0.35
     ostavi
    0.34
    Vidite
    0.34
     LCCN
    0.32
    Rptr
    0.31
    Activations Density 0.148%

    No Known Activations