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. 6912
    Prev
    Next
    INDEX
    Explanations

    attends to the use of tokens followed by a semicolon from other tokens in sequences

    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
    0:0.14
    1:0.17
    2:0.14
    3:0.07
    4:0.24
    5:0.06
    6:0.05
    7:0.10
    Negative Logits
    multer
    -0.49
     transférez
    -0.40
    EMPL
    -0.39
    atorio
    -0.38
     createState
    -0.38
    
    -0.38
    figer
    -0.37
    Quellen
    -0.37
    الإنجليزية
    -0.36
    ály
    -0.36
    POSITIVE LOGITS
     betweenstory
    0.43
    loroethene
    0.41
    BagConstraints
    0.39
    ieteur
    0.39
     ENS
    0.38
     schizophren
    0.36
    roek
    0.36
     PVP
    0.35
    tigungs
    0.35
     CMC
    0.35
    Activations Density 0.158%

    No Known Activations