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. 5-GEMMASCOPE-RES-16K
    6. 15518
    Prev
    Next
    INDEX
    Explanations

    expressions related to the passage of days and routines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spotify
    -0.70
     dit
    -0.65
     Bic
    -0.60
     el
    -0.60
    youtu
    -0.57
    jupiter
    -0.57
    ><!--
    -0.54
     au
    -0.54
    assium
    -0.53
    Bic
    -0.53
    POSITIVE LOGITS
     disambiguazione
    1.13
    Everyday
    1.04
     everytime
    0.97
     everyday
    0.97
    everyday
    0.96
     itſelf
    0.84
     Everyday
    0.84
     annually
    0.83
     Majefty
    0.82
     myſelf
    0.81
    Activations Density 0.059%

    No Known Activations