© 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. 23-GEMMASCOPE-RES-16K
    11. 8318
    Prev
    Next
    INDEX
    Explanations

    phrases that denote a limited quantity of time or number

    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
    2
    -0.51
     helft
    -0.48
    diging
    -0.48
     lèvres
    -0.48
     dieux
    -0.44
    7
    -0.44
    4
    -0.43
     totales
    -0.43
    3
    -0.42
    1
    -0.42
    POSITIVE LOGITS
     hundred
    1.69
     dozen
    1.52
     thousand
    1.42
    hundred
    1.35
    dozen
    1.23
    thousand
    1.19
     hundert
    1.15
     weeks
    1.11
    Hundred
    1.03
     inches
    0.97
    Activations Density 0.088%

    No Known Activations