© 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. 20-GEMMASCOPE-RES-16K
    11. 6263
    Prev
    Next
    INDEX
    Explanations

    SQL database operations and commands

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

    SQL queries or SQL-related code

    np_acts-logits-general · gemini-2.0-flash

    SQL SELECT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    •SQL-labeled features

    No Comments

    Negative Logits
    endforeach
    -0.70
    posedge
    -0.70
    adaptiveStyles
    -0.69
     lenker
    -0.68
    ++]=
    -0.67
    تقاوى
    -0.66
    </>
    -0.65
    PerformLayout
    -0.64
     endforeach
    -0.64
    :+:
    -0.64
    POSITIVE LOGITS
    SELECT
    0.80
    select
    0.79
    Select
    0.69
     select
    0.69
     SELECT
    0.63
     selecting
    0.61
    олові
    0.54
     Select
    0.53
     seleccionar
    0.52
     sélectionner
    0.51
    Activations Density 0.075%

    No Known Activations