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. 6079
    Prev
    Next
    INDEX
    Explanations

    attends to superlative adjectives from nouns indicating a category or group

    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
    0:0.11
    1:0.16
    2:0.10
    3:0.08
    4:0.08
    5:0.04
    6:0.09
    7:0.30
    Negative Logits
     AssemblyCulture
    -0.56
    SequentialGroup
    -0.54
    +:+
    -0.52
    AndEndTag
    -0.47
    AnchorStyles
    -0.46
    IUrlHelper
    -0.46
    UrlResolution
    -0.45
     дописавши
    -0.44
     الحره
    -0.44
    ngdoc
    -0.44
    POSITIVE LOGITS
    span
    0.24
    k
    0.23
    ir
    0.23
    if
    0.23
     forma
    0.23
    ss
    0.23
    r
    0.23
    che
    0.22
     puissiez
    0.22
    ling
    0.22
    Activations Density 0.359%

    No Known Activations