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. 6161
    Prev
    Next
    INDEX
    Explanations

    attends to location-related tokens from tokens that describe a product or service

    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
    0:0.17
    1:0.24
    2:0.14
    3:0.07
    4:0.09
    5:0.03
    6:0.06
    7:0.15
    Negative Logits
    SequentialGroup
    -0.40
     plebis
    -0.28
    mige
    -0.28
     Tôi
    -0.28
    XDECREF
    -0.28
    AnchorStyles
    -0.27
     iod
    -0.26
    theless
    -0.26
    xffffffff
    -0.26
    Bust
    -0.25
    POSITIVE LOGITS
    MigrationBuilder
    0.33
    webElementXpaths
    0.27
    tvguidetime
    0.26
    awaiter
    0.24
    dataIndex
    0.24
    ariate
    0.23
    лтамалар
    0.23
    ManyToOne
    0.23
    /$
    0.22
    RequiresApi
    0.21
    Activations Density 0.127%

    No Known Activations