© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 1980
    Prev
    Next
    INDEX
    Explanations

    phrases related to assistance and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quelcon
    -0.74
    GEBURTSDATUM
    -0.73
     חיצוניים
    -0.70
    IBarButtonItem
    -0.68
     aéri
    -0.65
    הערות
    -0.65
    ftagPool
    -0.62
    Véxase
    -0.62
    PostExecute
    -0.62
     resourceCulture
    -0.61
    POSITIVE LOGITS
     help
    2.10
     helping
    2.00
     helps
    1.89
    Helping
    1.83
    help
    1.75
     Help
    1.75
    helping
    1.70
    Help
    1.70
     Helping
    1.67
     Helps
    1.65
    Activations Density 0.095%

    No Known Activations