© 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. 1955
    Prev
    Next
    INDEX
    Explanations

    specific product announcements or releases, particularly in the automotive or gaming sectors

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

    announcements or reveals

    np_acts-logits-general · gemini-2.0-flash

    announcements and previews

    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
    صحاب
    -0.60
     Pareto
    -0.55
    ★★★★★
    -0.51
     UPM
    -0.50
     loto
    -0.49
     semej
    -0.48
     Banach
    -0.48
     genocide
    -0.48
     ör
    -0.48
     onBackPressed
    -0.47
    POSITIVE LOGITS
     teaser
    1.30
     teased
    1.18
     reveal
    1.09
     tease
    1.08
    teaser
    1.07
     revealed
    1.06
     unveiling
    1.03
     hinting
    1.02
     unveil
    1.02
     preview
    0.99
    Activations Density 0.116%

    No Known Activations