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

    Neuronpedia

    APICircuit 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. 0-GEMMASCOPE-ATT-16K
    6. 418
    Prev
    Next
    INDEX
    Explanations

    attends to the token "post" from various related tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-att-16k
    Configuration
    google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.attn.hook_z
    Hook Layer
    0
    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
    0:0.11
    1:0.01
    2:0.02
    3:0.02
    4:0.74
    5:0.02
    6:0.02
    7:0.02
    Negative Logits
     يتيمه
    -0.54
    InputBorder
    -0.45
    PhysRevD
    -0.44
     BorderSide
    -0.43
    extAlignment
    -0.43
    khó
    -0.43
    phide
    -0.42
    ChildScrollView
    -0.42
     AssemblyCompany
    -0.41
     newBuilder
    -0.41
    POSITIVE LOGITS
    ImageContext
    0.40
    SOUNDBITE
    0.38
     gloire
    0.37
    ↵↵
    0.36
    yntaxException
    0.35
    fristig
    0.32
     sembler
    0.32
    printLine
    0.31
    Попис
    0.30
     تعدى
    0.29
    Activations Density 0.090%

    No Known Activations