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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 4827
    Prev
    Next
    INDEX
    Explanations

    instances of the word "throughout" and its variants indicating extent across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    n
    -0.77
     “
    -0.74
    a
    -0.74
    al
    -0.71
    o
    -0.69
     –
    -0.67
    2
    -0.67
     "
    -0.66
    /
    -0.66
     sal
    -0.66
    POSITIVE LOGITS
    throughout
    1.66
    HOUT
    1.39
     throughout
    1.39
     Throughout
    1.25
    Throughout
    1.24
    MLLoader
    1.21
     myſelf
    1.10
     defaultstate
    1.10
     itſelf
    1.09
    InputBorder
    1.04
    Activations Density 0.076%

    No Known Activations