© 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. 18-GEMMASCOPE-RES-16K
    11. 14996
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the initiation or recommendation of actions or processes

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

    followed by "start" or related terms

    np_acts-logits-general · gemini-2.0-flash

    starting and first steps

    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
    [](
    -0.59
    JspWriter
    -0.53
    addPreferredGap
    -0.51
     beroep
    -0.48
    Scrolled
    -0.47
    StructEnd
    -0.46
    треть
    -0.45
    TagMode
    -0.44
    Gizmos
    -0.43
    forName
    -0.42
    POSITIVE LOGITS
     start
    1.70
     starters
    1.57
     starting
    1.50
     begin
    1.50
     starts
    1.49
     Start
    1.47
    Start
    1.44
    start
    1.42
     starter
    1.40
     first
    1.40
    Activations Density 0.327%

    No Known Activations