© 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. 14920
    Prev
    Next
    INDEX
    Explanations

    terms related to financial and legal concepts

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

    preceding a percentage or other symbol

    np_acts-logits-general · gemini-2.0-flash

    study, index, application, Dakota, edge, elements

    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
     propOrder
    -1.15
    adaptiveStyles
    -1.11
     snippetHide
    -1.09
    AddTagHelper
    -1.06
     nahilalakip
    -1.06
     disambiguazione
    -1.04
    +#+
    -1.04
    ьаж
    -1.03
    contentLoaded
    -1.01
    SourceChecksum
    -0.97
    POSITIVE LOGITS
    참고
    0.51
    fflush
    0.48
    кновен
    0.44
    IfNeeded
    0.43
     rom
    0.43
    OfDay
    0.42
     espar
    0.42
     Ú
    0.42
    InBytes
    0.42
    zum
    0.41
    Activations Density 1.968%

    No Known Activations