© 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. 22-GEMMASCOPE-RES-16K
    11. 7510
    Prev
    Next
    INDEX
    Explanations

    terms related to health, tax policy, and online gambling

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

    preceding a problem, area, or decision

    np_acts-logits-general · gemini-2.0-flash

    research problem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     réguli
    -0.85
     scolaires
    -0.79
     définiti
    -0.78
    findpost
    -0.77
     religieuses
    -0.77
     récomp
    -0.76
     malheure
    -0.75
     malheureux
    -0.75
     médec
    -0.74
     normaux
    -0.74
    POSITIVE LOGITS
    -
    0.68
    -​
    0.60
     nakalista
    0.59
    related
    0.58
    atguigu
    0.55
    ISODE
    0.53
    <bos>
    0.53
    quiao
    0.51
    quiel
    0.49
    Autoritní
    0.47
    Activations Density 1.579%

    No Known Activations