Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 2871
    Prev
    Next
    INDEX
    Explanations

    greeting phrases and expressions of welcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelper
    -0.68
    GroupLayout
    -0.60
    ftagPool
    -0.59
    lismo
    -0.56
    rootDir
    -0.56
     kas
    -0.56
    LookAnd
    -0.55
     يتيمه
    -0.52
    ühen
    -0.51
    olverine
    -0.50
    POSITIVE LOGITS
    elcome
    0.93
     welcome
    0.85
     Willkommen
    0.77
    WELCOME
    0.77
    welcome
    0.76
     aboard
    0.76
     Welcome
    0.76
     velkommen
    0.75
     bienvenida
    0.74
    Bienvenido
    0.74
    Activations Density 0.053%

    No Known Activations