© 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. 23-GEMMASCOPE-RES-16K
    11. 15386
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to data analysis and measurement errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pology
    -0.54
    ConstraintMaker
    -0.50
     promessa
    -0.46
    yelidikan
    -0.45
     profesión
    -0.43
     caractéris
    -0.43
     Hamlin
    -0.43
    NSData
    -0.42
     abandonado
    -0.42
    itom
    -0.42
    POSITIVE LOGITS
     effects
    1.06
    effects
    0.88
     noise
    0.87
     interference
    0.87
     errors
    0.83
     effets
    0.83
     effect
    0.83
     inaccuracies
    0.81
     efeitos
    0.80
     Effects
    0.80
    Activations Density 2.315%

    No Known Activations