© 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. 5707
    Prev
    Next
    INDEX
    Explanations

    terminology related to medical and psychological conditions, particularly chronic diseases and stereotypes

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

    with suffixes (-al, -on, -ible, -ment, -ropy, -own)

    np_acts-logits-general · gemini-2.0-flash

    word stems forming English 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
    ⓧ
    -0.93
    sizeCache
    -0.89
     EconPapers
    -0.88
     "..\..\..\
    -0.84
     mergeFrom
    -0.81
    ★★★★☆
    -0.77
    WebServlet
    -0.74
    addContainerGap
    -0.72
     Réponses
    -0.70
     "..\..\
    -0.69
    POSITIVE LOGITS
    entibus
    0.73
    ſtra
    0.67
    ſel
    0.65
     détru
    0.64
    ésult
    0.62
    ſem
    0.60
    geſ
    0.59
     iſt
    0.58
     féd
    0.58
     fourrure
    0.56
    Activations Density 1.077%

    No Known Activations