© 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. 18-GEMMASCOPE-RES-16K
    11. 8794
    Prev
    Next
    INDEX
    Explanations

    time-related phrases or references to temporal context

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

    Years

    np_acts-logits-general · gemini-2.0-flash

    past years and earlier times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndInit
    -0.76
     Majefty
    -0.75
    ClientSize
    -0.69
    RTEX
    -0.67
    GEBURTSDATUM
    -0.66
    rungsseite
    -0.60
     NSCoder
    -0.58
     forthcoming
    -0.58
    andaag
    -0.57
    よいよ
    -0.57
    POSITIVE LOGITS
     förra
    0.84
     earlier
    0.81
     last
    0.76
     scorso
    0.72
     fjor
    0.68
     прошлого
    0.68
    earlier
    0.66
     прошлом
    0.65
     Earlier
    0.65
    去年
    0.65
    Activations Density 0.160%

    No Known Activations