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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12265
    Prev
    Next
    INDEX
    Explanations

    principles related to regulations and guidelines, specifically in a legal or environmental context

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

    "principle" or "principles"

    np_acts-logits-general · gemini-2.0-flash

    principle

    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
     nakalista
    -0.64
    جه
    -0.48
     nahilalakip
    -0.48
    <()>
    -0.48
     équipement
    -0.46
     disambiguazione
    -0.45
     PeEnEo
    -0.44
     elek
    -0.44
    cler
    -0.44
     comuniques
    -0.44
    POSITIVE LOGITS
     principle
    2.11
     principles
    2.05
    principles
    1.84
    principle
    1.82
     Principle
    1.77
    Principle
    1.75
     Principles
    1.73
    Principles
    1.65
     concept
    1.59
     principe
    1.56
    Activations Density 0.448%

    No Known Activations