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-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 2940
    Prev
    Next
    INDEX
    Explanations

    instances of the word "summary" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Föld
    -0.38
    ạp
    -0.36
    posedge
    -0.34
    *)((
    -0.33
     partout
    -0.33
    FirebaseDatabase
    -0.33
    CHREIB
    -0.33
    Erreferentziak
    -0.32
     phone
    -0.32
    Fø
    -0.32
    POSITIVE LOGITS
    summary
    2.89
     summary
    2.30
     Summary
    2.09
    Summary
    2.09
     SUMMARY
    1.88
    SUMMARY
    1.82
     summaries
    1.76
     summarize
    1.52
     summarised
    1.51
     summarized
    1.50
    Activations Density 0.025%

    No Known Activations