© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 918
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols

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

    mathematical and statistical language related to data analysis and computational reasoning.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    mathematical expressions and statements that describe logical relationships, particularly focusing on words like "depends", "affects", "involves", "interfere" and other terms showing connections between variables.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PDS
    -0.39
     DSG
    -0.39
     PDB
    -0.38
    CORBA
    -0.37
    Viitteet
    -0.37
     calyx
    -0.36
     fusca
    -0.36
    ‬
    -0.36
     Erg
    -0.35
     CPR
    -0.35
    POSITIVE LOGITS
     Bewußt
    0.62
     navíc
    0.59
     Genuss
    0.56
     geométrico
    0.56
     geomé
    0.56
     Vordergrund
    0.54
     Zugang
    0.51
     coûts
    0.51
     relatifs
    0.50
     compleja
    0.50
    Activations Density 2.420%

    No Known Activations