© 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. 20-GEMMASCOPE-RES-16K
    11. 4534
    Prev
    Next
    INDEX
    Explanations

    phrases related to errors in image processing or loading

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

    Lithuanian language or location

    np_acts-logits-general · gemini-2.0-flash

    Lithuania University Defense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -1.26
     myſelf
    -1.23
     purpoſe
    -1.23
     raiſ
    -1.20
     itſelf
    -1.19
     Majefty
    -1.17
     Reſ
    -1.16
    ſelf
    -1.15
     faſt
    -1.14
     Anſ
    -1.13
    POSITIVE LOGITS
     ir
    0.60
     „
    0.51
     did
    0.48
     d
    0.46
     bei
    0.44
     su
    0.43
    webElement
    0.42
     «
    0.42
     nor
    0.41
     de
    0.39
    Activations Density 0.090%

    No Known Activations