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. 5874
    Prev
    Next
    INDEX
    Explanations

    attends to the token "testcase" from the token "building."

    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
    0:0.06
    1:0.10
    2:0.09
    3:0.13
    4:0.10
    5:0.04
    6:0.28
    7:0.15
    Negative Logits
    <?
    -0.35
    OnInit
    -0.34
     gestes
    -0.33
    ContextHolder
    -0.33
    তথ্যসূত্র
    -0.33
    Autoritní
    -0.33
    AddField
    -0.32
    Vidite
    -0.31
     siè
    -0.31
     scher
    -0.31
    POSITIVE LOGITS
     Audiodateien
    0.56
    DockStyle
    0.43
     }}$}
    0.43
    *********/
    0.42
    SequentialGroup
    0.42
    GeneratedMessage
    0.42
    ')]
    0.40
    THON
    0.39
    ][-
    0.39
    )|^{
    0.39
    Activations Density 0.001%

    No Known Activations