© 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. 8215
    Prev
    Next
    INDEX
    Explanations

    elements related to traffic and driving experiences

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

    associated with reversing direction

    np_acts-logits-general · gemini-2.0-flash

    forward and backward movement

    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
    Rhestr
    -0.74
    älde
    -0.56
    τύ
    -0.54
    AutoScaleMode
    -0.53
     createState
    -0.53
     getItemCount
    -0.53
    sizeCache
    -0.52
     disambiguazione
    -0.52
    исленность
    -0.52
    Necesito
    -0.52
    POSITIVE LOGITS
     reverse
    1.84
     Reverse
    1.59
    reverse
    1.55
    Reverse
    1.52
     reversed
    1.47
     reversing
    1.35
     backwards
    1.32
     inverse
    1.31
    reversed
    1.28
     return
    1.27
    Activations Density 0.356%

    No Known Activations