© 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. 10-GEMMASCOPE-RES-16K
    11. 3380
    Prev
    Next
    INDEX
    Explanations

    the word "there" in various contexts and frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    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

    Negative Logits
    dom
    -0.67
     getSub
    -0.61
    ly
    -0.59
    endphp
    -0.58
     of
    -0.58
    Appendix
    -0.56
     N
    -0.56
    APE
    -0.55
    quot
    -0.55
    APPENDIX
    -0.54
    POSITIVE LOGITS
     autorytatywna
    1.09
     frattempo
    0.92
     THERE
    0.91
    ειτουργ
    0.90
     Allí
    0.90
     berdua
    0.89
     समीक्षक
    0.87
     there
    0.86
     חיצוניים
    0.83
     CreateTagHelper
    0.83
    Activations Density 0.082%

    No Known Activations