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. 1
    Prev
    Next
    INDEX
    Explanations

    attends to characters or terms related to user libraries from additional library elements

    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
    0:0.03
    1:0.04
    2:0.05
    3:0.08
    4:0.04
    5:0.53
    6:0.12
    7:0.07
    Negative Logits
     fund
    -0.26
    '
    -0.24
    wä
    -0.23
    "
    -0.23
     Fiche
    -0.22
     تق
    -0.22
     houſe
    -0.22
     house
    -0.22
    askin
    -0.22
    )";
    
    -0.21
    POSITIVE LOGITS
    TagMode
    0.53
    AnchorTagHelper
    0.46
    :✨
    0.44
    TypedDataSet
    0.44
    SpringRunner
    0.44
    دانشنامهٔ
    0.43
    WithIOException
    0.42
    ConstraintMaker
    0.42
    adpleegd
    0.41
     otomatig
    0.41
    Activations Density 0.021%

    No Known Activations