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. 6441
    Prev
    Next
    INDEX
    Explanations

    attends to various copyright tokens from corresponding company or organization 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
    0:0.08
    1:0.11
    2:0.10
    3:0.05
    4:0.06
    5:0.02
    6:0.11
    7:0.43
    Negative Logits
    存于互联网档案馆
    -0.44
    DockStyle
    -0.43
     CreateTagHelper
    -0.42
    __(/*!
    -0.42
    AndEndTag
    -0.41
    AddHtmlAttribute
    -0.41
    SequentialGroup
    -0.41
    ніципалі
    -0.40
     PLAINTIFF
    -0.40
    SceneManagement
    -0.39
    POSITIVE LOGITS
    toma
    0.29
     ajuns
    0.28
     природы
    0.27
    بوب
    0.27
     být
    0.26
    MenuView
    0.26
     darken
    0.26
    гы
    0.26
    ERGY
    0.26
    onAdd
    0.25
    Activations Density 0.046%

    No Known Activations