© 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. 15-GEMMASCOPE-RES-16K
    11. 12969
    Prev
    Next
    INDEX
    Explanations

    concepts related to comparison and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StackNavigator
    -0.49
    rix
    -0.49
     ơn
    -0.47
    جيل
    -0.45
    DataSnapshot
    -0.45
    ipel
    -0.45
    ymce
    -0.44
    낭
    -0.44
    Autoritní
    -0.43
     Avion
    -0.43
    POSITIVE LOGITS
     importantly
    1.39
    何より
    1.16
     Importantly
    1.00
     soprattutto
    0.92
     surtout
    0.88
     moreover
    0.87
     przede
    0.81
     главное
    0.80
     secondly
    0.80
     furthermore
    0.77
    Activations Density 0.174%

    No Known Activations