© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13103
    Prev
    Next
    INDEX
    Explanations

    phrases indicating continuation or persistence in actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by "to"

    np_acts-logits-general · gemini-2.0-flash

    continue to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     begint
    -0.72
     zač
    -0.68
     begy
    -0.66
     anfangen
    -0.66
     begin
    -0.65
     börja
    -0.65
     begins
    -0.64
     înce
    -0.63
     beginning
    -0.63
    ksikon
    -0.63
    POSITIVE LOGITS
     unab
    0.89
    下去
    0.78
     indefinitely
    0.64
     uninterrupted
    0.62
     unbroken
    0.61
     efforts
    0.61
     unchanged
    0.60
     forward
    0.59
     onward
    0.59
     until
    0.59
    Activations Density 0.091%

    No Known Activations