© 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. 13917
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conclusions or summaries

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

    Tokens after abbreviations or citations

    np_acts-logits-general · gemini-2.0-flash

    introducing a summary or explanation

    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
     vectorielles
    -0.68
     useAuth
    -0.67
    ClientSize
    -0.64
     betweenstory
    -0.62
    ConstraintMaker
    -0.60
    LEncoder
    -0.59
     évek
    -0.59
     auroit
    -0.59
     électroniques
    -0.58
    withIdentifier
    -0.57
    POSITIVE LOGITS
     Briefly
    1.18
    Basically
    1.03
     Basically
    1.02
    Essentially
    1.01
     Essentially
    0.94
     basically
    0.93
     gist
    0.93
    basically
    0.83
     essentially
    0.83
     Danach
    0.82
    Activations Density 0.567%

    No Known Activations