© 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. 5-GEMMASCOPE-RES-16K
    11. 14827
    Prev
    Next
    INDEX
    Explanations

    the word "otherwise" and its variations, indicating a focus on conditional or alternative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    et
    -0.61
    obium
    -0.59
    cmath
    -0.59
    gido
    -0.58
     Stur
    -0.56
    dymyr
    -0.55
    hat
    -0.54
    1
    -0.53
    m
    -0.53
    лябин
    -0.52
    POSITIVE LOGITS
     otherwise
    2.13
    otherwise
    2.06
    Otherwise
    2.05
     Otherwise
    2.01
     OTHERWISE
    1.96
     altrimenti
    1.54
     иначе
    1.21
     ellers
    1.18
     sonst
    1.17
    不然
    1.15
    Activations Density 0.076%

    No Known Activations