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. 176
    Prev
    Next
    INDEX
    Explanations

    attends to position-related tokens from positional markers that appear later in the sequences

    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
    0:0.81
    1:0.01
    2:0.01
    3:0.02
    4:0.08
    5:0.01
    6:0.01
    7:0.02
    Negative Logits
     of
    -0.34
     at
    -0.30
     the
    -0.30
     on
    -0.29
     in
    -0.28
     autorytatywna
    -0.27
     not
    -0.27
     him
    -0.27
     a
    -0.27
     
    -0.27
    POSITIVE LOGITS
    StoryboardSegue
    0.64
     فريبيس
    0.52
    AddTagHelper
    0.52
    GOTREF
    0.48
    脚注の使い方
    0.47
     crossorigin
    0.46
    URLException
    0.44
     JpaRepository
    0.44
     fVar
    0.43
    tvguidetime
    0.43
    Activations Density 0.042%

    No Known Activations