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. 46
    Prev
    Next
    INDEX
    Explanations

    attends to the term "band" from various technical and scientific contexts followed by specific measurements or references such as "pass" or "gap."

    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
    0:0.68
    1:0.01
    2:0.02
    3:0.02
    4:0.16
    5:0.03
    6:0.01
    7:0.02
    Negative Logits
    hrer
    -0.30
     Архивировано
    -0.29
    providedIn
    -0.28
     cá
    -0.27
    UMNS
    -0.27
    jsxFileName
    -0.26
     semp
    -0.26
    iants
    -0.26
    تقاوى
    -0.26
     anh
    -0.26
    POSITIVE LOGITS
     autorytatywna
    0.45
     دیکھیے
    0.40
     îna
    0.39
    elesai
    0.38
    glEnd
    0.35
    ImageContext
    0.35
     ModelRenderer
    0.35
     '');
    0.35
     sababu
    0.35
     fédé
    0.34
    Activations Density 0.008%

    No Known Activations