© 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. 15895
    Prev
    Next
    INDEX
    Explanations

    successful outcomes of events or procedures

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

    Follows forms of the word "go"

    np_acts-logits-general · gemini-2.0-flash

    smooth progression

    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
     depra
    -0.46
     ContentValues
    -0.46
     abstain
    -0.46
     chastity
    -0.45
    hnia
    -0.45
    ására
    -0.44
     fals
    -0.43
     Pharisees
    -0.43
    यार
    -0.43
    ListModule
    -0.42
    POSITIVE LOGITS
     smooth
    1.71
     smoothly
    1.67
     Smooth
    1.51
    Smooth
    1.45
     smoother
    1.44
    smooth
    1.41
     smoothness
    1.29
     successful
    1.15
     seamless
    1.13
     lancar
    1.07
    Activations Density 0.215%

    No Known Activations