© 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. 18-GEMMASCOPE-RES-16K
    11. 15566
    Prev
    Next
    INDEX
    Explanations

    terms related to biological processes and programming concepts

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

    Rates, execution, growth, projection, transmission, or combustion

    np_acts-logits-general · gemini-2.0-flash

    execution and parameters

    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
     חיצוניים
    -0.76
    الإنجليزية
    -0.70
    gehalt
    -0.68
    Stiftung
    -0.66
    occuper
    -0.62
     كومونز
    -0.62
     épaules
    -0.62
     oreilles
    -0.61
     imageNamed
    -0.61
     مرئيه
    -0.60
    POSITIVE LOGITS
     process
    0.69
    able
    0.61
    ability
    0.58
     quality
    0.56
     times
    0.53
     date
    0.51
     ability
    0.50
     time
    0.49
     methods
    0.49
     operation
    0.49
    Activations Density 1.145%

    No Known Activations