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. 6167
    Prev
    Next
    INDEX
    Explanations

    attends to the token "throw" from the token "Exception."

    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
    0:0.11
    1:0.04
    2:0.04
    3:0.02
    4:0.22
    5:0.46
    6:0.03
    7:0.04
    Negative Logits
     itſelf
    -0.65
     myſelf
    -0.65
     houſe
    -0.65
     Efq
    -0.64
     themſelves
    -0.57
     Monfieur
    -0.56
     ſmall
    -0.55
     Houſe
    -0.54
     ſtate
    -0.54
    ſelf
    -0.54
    POSITIVE LOGITS
    verwijspagina
    0.41
     ‘
    0.39
    NameInMap
    0.39
    UnusedPrivate
    0.36
    ;
    0.34
    );
    0.34
     ***!
    0.33
    ');
    0.32
     );
    0.32
    PreferredItem
    0.31
    Activations Density 0.017%

    No Known Activations