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. 367
    Prev
    Next
    INDEX
    Explanations

    attends to mathematical expressions containing specific patterns from the following tokens

    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
    0:0.02
    1:0.10
    2:0.09
    3:0.26
    4:0.06
    5:0.05
    6:0.31
    7:0.07
    Negative Logits
     $
    -0.75
     \
    -0.58
    ]\\
    -0.57
     $-
    -0.56
    \]
    -0.56
    }\
    -0.55
    $
    -0.54
     \\
    -0.53
     $.
    -0.52
    )$
    -0.51
    POSITIVE LOGITS
     الرياضيه
    0.71
    SpringBootTest
    0.64
     Divulgação
    0.60
     étoient
    0.59
     avoient
    0.58
    GEBURTSDATUM
    0.57
     NSCoder
    0.56
    Enders
    0.54
    StructEnd
    0.54
     preocupes
    0.54
    Activations Density 16.724%

    No Known Activations