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. 6020
    Prev
    Next
    INDEX
    Explanations

    attends to the folder paths and specific errors associated with file locations and code issues from the commands issued in the sequence

    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
    0:0.11
    1:0.18
    2:0.09
    3:0.04
    4:0.09
    5:0.31
    6:0.04
    7:0.09
    Negative Logits
    +#+#
    -0.41
     AssemblyTitle
    -0.38
     kasarigan
    -0.38
    parsedMessage
    -0.37
    modelBuilder
    -0.37
    ApiProperty
    -0.37
     initComponents
    -0.36
    CodedInputStream
    -0.36
    UnsafeEnabled
    -0.35
     kaynağından
    -0.35
    POSITIVE LOGITS
    arraycopy
    0.24
    oder
    0.24
    UNCIL
    0.24
    mets
    0.24
     Mank
    0.23
    kur
    0.23
    recyclerView
    0.22
    kug
    0.22
    án
    0.22
     dira
    0.21
    Activations Density 0.029%

    No Known Activations