© 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 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. 3199
    Prev
    Next
    INDEX
    Explanations

    terms related to standardization and objectification in research contexts

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

    words related to methodological and technical terms, particularly those associated with scholarly or scientific contexts.

    oai_token-act-pair · gpt-4oTriggered by @christianthto

    ending in "tive", "ative", or "ivity"

    np_acts-logits-general · gemini-2.0-flash

    words ending in -tive or -vely

    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
    tagHelperRunner
    -0.80
     endforeach
    -0.68
    uxxxx
    -0.62
    脚注の使い方
    -0.61
    Vidite
    -0.60
     disambiguazione
    -0.59
    Бахар
    -0.58
    saraba
    -0.57
    GraphicsUnit
    -0.55
    ########.
    -0.54
    POSITIVE LOGITS
    tive
    1.25
    IVE
    1.20
    ive
    1.16
    ative
    1.15
    ATIVE
    1.08
    tives
    1.06
     tive
    1.06
    itive
    1.03
    itve
    0.98
     active
    0.98
    Activations Density 0.256%

    No Known Activations