© 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. 14869
    Prev
    Next
    INDEX
    Explanations

    elements of email formatting and etiquette guidelines

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

    Followed by curly brackets or related to email recipients

    np_acts-logits-general · gemini-2.0-flash

    recipients, cc, addressed

    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
    ConstraintMaker
    -0.82
    ContentAsync
    -0.79
     indisponible
    -0.78
     دیکھیے
    -0.72
    IntoConstraints
    -0.70
    GeoNames
    -0.65
    >\<^
    -0.64
     newOwner
    -0.64
     simplifié
    -0.64
    Népesség
    -0.63
    POSITIVE LOGITS
    cc
    0.88
     addressee
    0.87
     cc
    0.84
    Cc
    0.77
     recipients
    0.76
     copied
    0.76
     copy
    0.73
     addressed
    0.70
     sender
    0.68
     recipient
    0.68
    Activations Density 0.457%

    No Known Activations