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. 6144
    Prev
    Next
    INDEX
    Explanations

    attends to the concept of "knowing" in relation to various later expressions of uncertainty or awareness

    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
    0:0.50
    1:0.01
    2:0.01
    3:0.01
    4:0.24
    5:0.13
    6:0.01
    7:0.03
    Negative Logits
    VIAF
    -0.43
    rrggbb
    -0.41
    hdashline
    -0.38
    ///</
    -0.37
     мәкал
    -0.37
    іга
    -0.35
    ISupport
    -0.34
    writeField
    -0.34
     اكتوبر
    -0.34
     hinaus
    -0.34
    POSITIVE LOGITS
    BagLayout
    0.39
    les
    0.28
     Auger
    0.27
     nô
    0.26
    +:+
    0.26
    Населення
    0.25
     parti
    0.25
     Haram
    0.25
    сла
    0.25
     bên
    0.24
    Activations Density 0.014%

    No Known Activations