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. 10-GEMMASCOPE-ATT-16K
    6. 6160
    Prev
    Next
    INDEX
    Explanations

    attends to the token "the" from various surrounding tokens

    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
    0:0.07
    1:0.08
    2:0.07
    3:0.08
    4:0.07
    5:0.03
    6:0.34
    7:0.22
    Negative Logits
    OGND
    -0.51
    KURZBESCHREIBUNG
    -0.45
     propOrder
    -0.44
    principalColumn
    -0.43
     nakalista
    -0.37
     يتيمه
    -0.37
     besz
    -0.37
     Norse
    -0.36
    protoimpl
    -0.36
    WebVitals
    -0.36
    POSITIVE LOGITS
     Sit
    0.26
    ngdoc
    0.26
     Anyway
    0.25
    ècie
    0.24
    HasMaxLength
    0.24
    hereinafter
    0.24
     («
    0.24
    Afterwards
    0.24
     AssemblyTitle
    0.23
     Grand
    0.23
    Activations Density 1.705%

    No Known Activations