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. 6341
    Prev
    Next
    INDEX
    Explanations

    attends to instances of "from" related to return or coming back from diverse scenarios, from related contextual 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
    0:0.12
    1:0.14
    2:0.16
    3:0.10
    4:0.05
    5:0.02
    6:0.05
    7:0.32
    Negative Logits
     "");
    
    -0.28
     '');
    -0.27
     CURLOPT
    -0.25
     />";
    -0.25
    Tikang
    -0.24
     '',
    
    -0.24
    \"");
    -0.24
    ConnectionState
    -0.24
     nakalista
    -0.23
    TestClass
    -0.23
    POSITIVE LOGITS
    parsedMessage
    0.30
     perm
    0.23
    tadiene
    0.23
    auré
    0.22
    dification
    0.22
     Autorisations
    0.21
     propOrder
    0.21
    WireFormatLite
    0.21
    FormTagHelper
    0.21
     ruolo
    0.21
    Activations Density 0.127%

    No Known Activations