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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6096
    Prev
    Next
    INDEX
    Explanations

    attends to tokens related to "battery" from tokens related to "life" or "systems."

    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
    0:0.61
    1:0.01
    2:0.03
    3:0.02
    4:0.18
    5:0.09
    6:0.01
    7:0.01
    Negative Logits
    .*")]
    -0.42
     his
    -0.35
    Дереккөздер
    -0.34
    شهاد
    -0.34
     Roskov
    -0.33
     sea
    -0.32
     a
    -0.31
     I
    -0.31
    Kjelder
    -0.31
    GTCX
    -0.30
    POSITIVE LOGITS
     gambe
    0.43
     cappuccio
    0.41
     connaissances
    0.40
     investissements
    0.40
     passagers
    0.40
     spirituale
    0.39
     colorés
    0.39
     partecipare
    0.39
     pantaloni
    0.38
     Diſ
    0.38
    Activations Density 0.005%

    No Known Activations