Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6446
    Prev
    Next
    INDEX
    Explanations

    attends to tokens relating to "bar" from tokens tagged with brackets

    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
    0:0.10
    1:0.13
    2:0.13
    3:0.12
    4:0.12
    5:0.06
    6:0.14
    7:0.17
    Negative Logits
    tagHelperRunner
    -0.35
    LookAnd
    -0.35
     pleaſure
    -0.34
     Signalez
    -0.34
    esez
    -0.33
     houſe
    -0.33
     himſelf
    -0.32
     QtWidgets
    -0.31
     themſelves
    -0.31
     ſhe
    -0.30
    POSITIVE LOGITS
    GEBURTS
    0.28
    MessageTagHelper
    0.26
     públicas
    0.24
    TemporalType
    0.24
    rtz
    0.22
     елның
    0.22
    chinen
    0.22
    ophile
    0.22
     كومونز
    0.21
    getDoctrine
    0.21
    Activations Density 0.104%

    No Known Activations