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. 315
    Prev
    Next
    INDEX
    Explanations

    attends to the zero values from various technical parameters in the sequences

    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
    0:0.74
    1:0.06
    2:0.01
    3:0.01
    4:0.05
    5:0.04
    6:0.01
    7:0.05
    Negative Logits
    ↵
    -0.43
    ↵↵
    -0.43
    T
    -0.42
    K
    -0.41
    D
    -0.41
    L
    -0.40
    G
    -0.40
    The
    -0.39
    I
    -0.39
    C
    -0.39
    POSITIVE LOGITS
    AccessorTable
    0.68
     myſelf
    0.67
    BibitemShut
    0.65
     Efq
    0.63
    bibfield
    0.63
     <=",
    0.61
    CloseOperation
    0.59
     Monfieur
    0.58
    MLLoader
    0.56
    ]")]
    0.56
    Activations Density 0.063%

    No Known Activations