© 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. 14908
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to gamification and rewards in an HR context

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

    Tokens after "ir" or model names containing "ir"

    np_acts-logits-general · gemini-2.0-flash

    hr_gamification badges

    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
    guien
    -0.51
    templateUrl
    -0.48
     spit
    -0.46
    eseorang
    -0.45
    老大
    -0.45
    ometrica
    -0.45
     slot
    -0.45
     Connectez
    -0.44
     Draw
    -0.44
     McBride
    -0.44
    POSITIVE LOGITS
    fjspx
    0.78
    bcryptjs
    0.70
     internetowa
    0.67
    SharedDtor
    0.64
    (__('
    0.61
    RetentionPolicy
    0.59
     isInitialized
    0.59
     himo
    0.57
    +#+#
    0.56
    AntiForgeryToken
    0.55
    Activations Density 0.059%

    No Known Activations