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. 10-GEMMASCOPE-ATT-16K
    6. 6641
    Prev
    Next
    INDEX
    Explanations

    attends to tokens referring to individual people or groups from their corresponding pronouns or reference tokens

    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
    0:0.09
    1:0.20
    2:0.14
    3:0.17
    4:0.18
    5:0.05
    6:0.06
    7:0.09
    Negative Logits
     متعلقه
    -0.42
    AsUp
    -0.40
    før
    -0.36
    хьтан
    -0.34
    KURZBESCHREIBUNG
    -0.34
    ArgsConstructor
    -0.34
    adaptiveStyles
    -0.33
     HasFactory
    -0.33
    avoit
    -0.32
    mybatisplus
    -0.31
    POSITIVE LOGITS
    rrggbb
    0.39
    sizeCache
    0.37
    BoxShadow
    0.34
    ///</
    0.33
    HasBeenSet
    0.33
    usp
    0.33
    IPH
    0.32
     Dere
    0.32
    MetaObject
    0.32
     Basili
    0.31
    Activations Density 0.390%

    No Known Activations