© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 8508
    Prev
    Next
    INDEX
    Explanations

    sentences that contain pointers or references to data structures in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.04
     myſelf
    -0.95
     Efq
    -0.91
     uſed
    -0.90
    `,
    -0.85
    ing
    -0.85
     ་་
    -0.83
    '},
    -0.83
     Mahomet
    -0.82
     Culver
    -0.82
    POSITIVE LOGITS
     nonatomic
    0.98
     *
    0.97
    ****************
    0.91
    /**
    0.89
    CppMethod
    0.88
    DotNetBar
    0.88
     Rosenthal
    0.84
     Pio
    0.80
     Kit
    0.76
     Benitez
    0.75
    Activations Density 0.215%

    No Known Activations