© 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. 18-GEMMASCOPE-RES-16K
    11. 14021
    Prev
    Next
    INDEX
    Explanations

    phrases related to job listings and work conditions

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

    Work shifts and hours

    np_acts-logits-general · gemini-2.0-flash

    working hours and shifts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GenerationType
    -0.65
    UserScript
    -0.64
     esternos
    -0.63
     snippetHide
    -0.62
    LookAnd
    -0.61
    ɵɵ
    -0.60
     Efq
    -0.60
    MessageState
    -0.60
    fromnode
    -0.59
     Issus
    -0.59
    POSITIVE LOGITS
     shift
    1.10
     shifts
    1.06
     overtime
    0.99
     Shift
    0.97
     Shifts
    0.95
    Shift
    0.86
    shift
    0.86
    シフト
    0.85
     Schicht
    0.82
    shifts
    0.81
    Activations Density 0.279%

    No Known Activations