© 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. 4571
    Prev
    Next
    INDEX
    Explanations

    expressions related to troubleshooting and system errors

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

    French words related to problems

    np_acts-logits-general · gemini-2.0-flash

    problems or issues

    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
     Monfieur
    -1.57
     ainfi
    -1.35
     myſelf
    -1.26
     itſelf
    -1.25
     abstrait
    -1.22
     enfans
    -1.21
     Houſe
    -1.21
     religieuses
    -1.21
     Reſ
    -1.20
     Majefty
    -1.19
    POSITIVE LOGITS
     :
    0.80
     !
    0.72
     «
    0.67
     ?
    0.66
     :
    0.64
     ;
    0.62
    ï
    0.57
     tuto
    0.56
    Nb
    0.56
    }^{+\
    0.53
    Activations Density 0.843%

    No Known Activations