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. 5876
    Prev
    Next
    INDEX
    Explanations

    attends to function-related tokens from related preparer 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
    0:0.08
    1:0.07
    2:0.08
    3:0.05
    4:0.07
    5:0.03
    6:0.12
    7:0.46
    Negative Logits
    Lähteet
    -0.22
    fitrión
    -0.20
    ografija
    -0.20
    ,”
    -0.20
     חיצוניים
    -0.19
    página
    -0.19
     withRouter
    -0.19
     pureza
    -0.18
     Edelman
    -0.18
    InstrumentedTest
    -0.18
    POSITIVE LOGITS
    WEBPACK
    0.33
    requireNonNull
    0.28
    RTLD
    0.28
     Doi
    0.28
    AddTagHelper
    0.28
    脚注の使い方
    0.27
     digress
    0.27
     IBOutlet
    0.27
    ็จ
    0.26
    setVerticalGroup
    0.26
    Activations Density 0.797%

    No Known Activations