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. 5916
    Prev
    Next
    INDEX
    Explanations

    attends to the closing bracket token from earlier tokens with similar structures

    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
    0:0.07
    1:0.08
    2:0.06
    3:0.48
    4:0.06
    5:0.03
    6:0.07
    7:0.09
    Negative Logits
    ogical
    -0.43
    DataPropertyName
    -0.39
    NoSuchAlgorithm
    -0.39
     immen
    -0.36
     Thermostat
    -0.36
    KEYCODE
    -0.36
    Trama
    -0.35
     thermostat
    -0.35
    templateUrl
    -0.35
     Hohen
    -0.35
    POSITIVE LOGITS
    ">//
    0.56
     كومونز
    0.53
     برانيه
    0.46
     esternos
    0.43
    GOTREF
    0.39
    meanor
    0.39
    RTLU
    0.39
     culturelles
    0.35
    Cyfeiriadau
    0.35
     mères
    0.34
    Activations Density 0.221%

    No Known Activations