© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 8290
    Prev
    Next
    INDEX
    Explanations

    references to healthcare or medical issues

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

    following common words

    np_acts-logits-general · gemini-2.0-flash

    misspellings and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.40
     iſt
    -1.32
     myſelf
    -1.28
     quæ
    -1.27
     ſtate
    -1.27
     ſta
    -1.26
     whoſe
    -1.25
     ſche
    -1.24
     uſ
    -1.23
     ſy
    -1.22
    POSITIVE LOGITS
     alot
    1.10
     loosing
    1.03
     coté
    1.01
     میتوان
    0.94
     thier
    0.89
     todays
    0.86
     pò
    0.86
     diatas
    0.86
    慢慢的
    0.86
     distru
    0.85
    Activations Density 2.528%

    No Known Activations