© 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. 8225
    Prev
    Next
    INDEX
    Explanations

    terms related to socioeconomic status and financial metrics

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

    Preceding "high" relating to a level or status

    np_acts-logits-general · gemini-2.0-flash

    high income or high standards

    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
    رایی
    -0.59
    uitable
    -0.54
    viewDidLoad
    -0.53
     subjects
    -0.52
    FieldBuilder
    -0.51
    ORIAL
    -0.51
    getSubject
    -0.51
    umel
    -0.50
    စ်
    -0.49
    xffffffff
    -0.49
    POSITIVE LOGITS
     Roskov
    0.83
    Autoritní
    0.59
     importe
    0.52
     محفوظة
    0.51
     SEDS
    0.50
    FormTagHelper
    0.49
     Berührung
    0.48
    TargetException
    0.47
    ParallelGroup
    0.47
    ItemLayout
    0.47
    Activations Density 0.234%

    No Known Activations