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

    Neuronpedia

    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. 20-GEMMASCOPE-RES-16K
    11. 9060
    Prev
    Next
    INDEX
    Explanations

    expressions related to predictions or expectations about the future

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

    "[verb] to" or "gonna" expressing future actions

    np_acts-logits-general · gemini-2.0-flash

    going to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.42
     ro
    -0.41
     wr
    -0.41
     Италијани
    -0.38
     dr
    -0.38
    τισ
    -0.37
     Dr
    -0.37
    찍
    -0.36
    付款
    -0.36
    ci
    -0.36
    POSITIVE LOGITS
     gonna
    1.32
    gonna
    1.20
     GONNA
    1.12
     going
    1.10
     Gonna
    1.05
    Gonna
    0.93
     GOING
    0.86
    __(/*!
    0.82
    going
    0.81
    tvguidetime
    0.77
    Activations Density 0.130%

    No Known Activations