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. 5550
    Prev
    Next
    INDEX
    Explanations

    attends to area codes from numerical phone numbers

    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
    0:0.20
    1:0.29
    2:0.07
    3:0.04
    4:0.05
    5:0.02
    6:0.05
    7:0.24
    Negative Logits
    awtextra
    -0.65
    SequentialGroup
    -0.60
    +:+
    -0.49
    bootstrapcdn
    -0.48
    igneurs
    -0.47
     مشين
    -0.47
     للاسماء
    -0.45
    parseColor
    -0.45
     onCreateView
    -0.45
    chenkt
    -0.44
    POSITIVE LOGITS
    sy
    0.37
    ?”
    0.37
    ”
    0.36
    —“
    0.36
    the
    0.33
    sig
    0.32
    しまう
    0.32
    гы
    0.31
     glyphicon
    0.31
     ?”
    0.31
    Activations Density 0.034%

    No Known Activations