Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6455
    Prev
    Next
    INDEX
    Explanations

    attends to specific context-setting words from juxtaposed independent examples or statements

    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
    0:0.05
    1:0.06
    2:0.07
    3:0.12
    4:0.13
    5:0.04
    6:0.36
    7:0.12
    Negative Logits
     vPvB
    -0.36
     Staying
    -0.30
     hasattr
    -0.30
    tik
    -0.29
    GHIJKLM
    -0.29
    tikan
    -0.29
    Grants
    -0.28
     Stay
    -0.28
    amot
    -0.28
    nonatomic
    -0.28
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.50
    ThroughAttribute
    0.41
     оригіналу
    0.40
    بوابة
    0.39
    ;->
    0.38
    ImageContext
    0.38
    RegressionTest
    0.37
    :][
    0.36
    Демографія
    0.36
    AutoScaleMode
    0.35
    Activations Density 0.413%

    No Known Activations