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. 5555
    Prev
    Next
    INDEX
    Explanations

    attends to the token before a comma from the token following it

    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
    0:0.06
    1:0.07
    2:0.08
    3:0.14
    4:0.09
    5:0.05
    6:0.28
    7:0.19
    Negative Logits
    Искәрмәләр
    -0.30
    unduh
    -0.29
    ReusableCell
    -0.29
     mentale
    -0.28
     mentales
    -0.28
    contentLoaded
    -0.28
     Buddy
    -0.27
    Nuorodos
    -0.27
    WebElementEntity
    -0.26
     culturales
    -0.26
    POSITIVE LOGITS
    DebuggerStep
    0.35
    :✨
    0.35
    клопе
    0.34
    makeConstraints
    0.33
    ethene
    0.32
    Życiorys
    0.32
    opsida
    0.32
    flot
    0.31
    GHIJKLM
    0.31
     beliebt
    0.30
    Activations Density 0.035%

    No Known Activations