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. 5547
    Prev
    Next
    INDEX
    Explanations

    attends to the "while" loop keyword from conditions related to various looping constructs

    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
    0:0.13
    1:0.15
    2:0.07
    3:0.10
    4:0.05
    5:0.03
    6:0.12
    7:0.32
    Negative Logits
    RenderAtEndOf
    -0.34
     发表于
    -0.32
     kum
    -0.31
     للمعارف
    -0.30
     nakalista
    -0.29
    ähän
    -0.29
    mphs
    -0.27
     sympy
    -0.27
     लंब
    -0.27
     cjs
    -0.27
    POSITIVE LOGITS
     originaux
    0.32
    SourceChecksum
    0.32
     avoient
    0.31
    saraba
    0.31
     préféré
    0.30
     Cliquez
    0.30
     étoient
    0.30
     originali
    0.30
     sauvages
    0.30
     referenties
    0.30
    Activations Density 0.021%

    No Known Activations