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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5645
    Prev
    Next
    INDEX
    Explanations

    attends to tokens like "agreement" and "management" from tokens that are related to contracts and leadership styles

    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
    1:0.24
    2:0.15
    3:0.09
    4:0.08
    5:0.02
    6:0.07
    7:0.12
    Negative Logits
    دانشنامهٔ
    -0.35
    IonicModule
    -0.33
    AndEndTag
    -0.32
    RetentionPolicy
    -0.32
     HasFactory
    -0.31
    geslacht
    -0.31
     ProtoMessage
    -0.30
     Schult
    -0.30
    หวัด
    -0.30
    UrlEncoded
    -0.30
    POSITIVE LOGITS
    oughly
    0.38
     BoxDecoration
    0.36
     виправивши
    0.36
     ujednoznacz
    0.32
    __(/*!
    0.32
     Hawthorne
    0.32
    ✨:
    0.32
     SFP
    0.30
     QI
    0.30
     BBB
    0.29
    Activations Density 1.528%

    No Known Activations