© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 2411
    Prev
    Next
    INDEX
    Explanations

    specific names and terms related to characters or items in gaming and science fiction literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anskje
    -1.03
    knock
    -0.76
     knock
    -0.76
     krim
    -0.70
    zzata
    -0.67
    ivasan
    -0.67
    möbel
    -0.67
     justices
    -0.66
    ahy
    -0.65
     Annette
    -0.65
    POSITIVE LOGITS
    aarrggbb
    0.95
     defaultstate
    0.84
     nakalista
    0.76
     Paglinawan
    0.74
     DMT
    0.69
    Попис
    0.68
    NameInMap
    0.68
    elemField
    0.67
     صوتيه
    0.67
     فريبيس
    0.65
    Activations Density 6.655%

    No Known Activations