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. 6683
    Prev
    Next
    INDEX
    Explanations

    attends to the mathematical notation of variables from the variables that follow

    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
    0:0.09
    1:0.12
    2:0.10
    3:0.14
    4:0.10
    5:0.07
    6:0.15
    7:0.18
    Negative Logits
    dev
    -0.24
    lete
    -0.24
     Audiodateien
    -0.23
    letes
    -0.23
    sohn
    -0.23
    GPP
    -0.22
    вз
    -0.22
    tru
    -0.22
     tried
    -0.21
    ↵↵↵
    -0.21
    POSITIVE LOGITS
    AndEndTag
    0.46
    tagHelperRunner
    0.43
     تضيفلها
    0.38
    CodedInputStream
    0.38
     ligiloj
    0.34
    Havolalar
    0.33
    iNdEx
    0.32
    QMetaType
    0.32
    IGraphics
    0.32
     dAtA
    0.31
    Activations Density 0.817%

    No Known Activations