© 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. 12409
    Prev
    Next
    INDEX
    Explanations

    various forms of ideologies and philosophies, particularly those ending in "ism" or related suffixes

    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
    ंदीखरीदारी
    -0.80
    NUR
    -0.64
    e
    -0.62
    มาะ
    -0.62
    aile
    -0.61
    a
    -0.61
     engraçadas
    -0.59
    पया
    -0.59
     ProtoMessage
    -0.59
    InputBorder
    -0.59
    POSITIVE LOGITS
    ist
    1.31
    ists
    1.28
    ISTS
    1.25
    isms
    1.18
    IST
    1.13
    alist
    1.12
    ISM
    1.10
    ism
    1.09
    izm
    1.08
     ism
    1.02
    Activations Density 0.096%

    No Known Activations