© 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. 8-GEMMASCOPE-RES-16K
    11. 10700
    Prev
    Next
    INDEX
    Explanations

    instances of the word "help" and its variations, indicating a focus on assistance or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    -0.82
    يبة
    -0.80
     Wally
    -0.76
     Sten
    -0.74
    anair
    -0.73
    eries
    -0.73
    .*")]
    -0.72
    elektron
    -0.71
    hå
    -0.71
    Wally
    -0.70
    POSITIVE LOGITS
     help
    1.61
    help
    1.45
     HELP
    1.44
     helps
    1.40
     helping
    1.40
    HELP
    1.37
     Help
    1.36
    Helps
    1.33
    Helping
    1.33
    Help
    1.31
    Activations Density 0.085%

    No Known Activations