© 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. 16-GEMMASCOPE-RES-16K
    11. 14249
    Prev
    Next
    INDEX
    Explanations

    references and mentions of guides or guidance in various contexts

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

    "Guide" or "guidance" appearing at the start of titles, or alone

    np_acts-logits-general · gemini-2.0-flash

    guide and guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forbes
    -0.66
    Morrison
    -0.65
     Kras
    -0.61
    texttt
    -0.59
    RSpec
    -0.58
    textContent
    -0.57
    sps
    -0.57
    ForRow
    -0.56
    %%\
    -0.55
    n
    -0.55
    POSITIVE LOGITS
    Guides
    1.34
     Guides
    1.32
     guides
    1.26
    guides
    1.20
     guide
    1.19
    guide
    1.19
     guider
    1.18
     guid
    1.18
     Guide
    1.17
     GUIDE
    1.16
    Activations Density 0.106%

    No Known Activations