© 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. 20-GEMMASCOPE-RES-16K
    11. 7886
    Prev
    Next
    INDEX
    Explanations

    aspects related to customization and tailoring of services or products to individual needs

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

    Customization or individualization

    np_acts-logits-general · gemini-2.0-flash

    customizing and tailoring options

    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
    لن
    -0.51
    hees
    -0.48
     yayın
    -0.47
    propagation
    -0.47
    Propagation
    -0.46
    HomeAsUpEnabled
    -0.46
     Innocent
    -0.45
    спу
    -0.44
     ErrIntOverflow
    -0.44
     innocence
    -0.43
    POSITIVE LOGITS
     customize
    2.32
     customized
    2.31
     custom
    2.28
     customization
    2.28
     customizing
    2.15
     customised
    2.11
    custom
    2.10
     customise
    2.07
     Custom
    2.02
     Customized
    2.01
    Activations Density 0.496%

    No Known Activations