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. 403
    Prev
    Next
    INDEX
    Explanations

    attends to the token marked with a dot from any token reflecting additional information

    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
    0:0.02
    1:0.49
    2:0.07
    3:0.04
    4:0.06
    5:0.22
    6:0.04
    7:0.03
    Negative Logits
     Réponses
    -0.71
    :✨
    -0.67
     nakalista
    -0.66
     surla
    -0.64
     ExecuteAsync
    -0.63
    хьтан
    -0.63
    tagHelperRunner
    -0.61
    ⓧ
    -0.60
     الحره
    -0.59
    styleType
    -0.59
    POSITIVE LOGITS
     ejus
    0.47
    .
    0.40
     habet
    0.35
     blanches
    0.35
     whoſe
    0.34
     spirituale
    0.34
     suprême
    0.34
     omnia
    0.34
     ſhe
    0.33
    and
    0.33
    Activations Density 0.007%

    No Known Activations