© 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. 5-GEMMASCOPE-RES-16K
    6. 8400
    Prev
    Next
    INDEX
    Explanations

    terms related to ubiquitination and protein degradation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     препратки
    -0.68
    ftagPool
    -0.68
     <=",
    -0.66
    httphttps
    -0.65
    évaluateur
    -0.63
    Xna
    -0.63
    SPATH
    -0.63
     Seder
    -0.62
    GEBURTSDATUM
    -0.61
    Izvori
    -0.61
    POSITIVE LOGITS
     marked
    0.99
     markiert
    0.88
     earmarked
    0.86
     tagged
    0.86
    Tagged
    0.84
     identifies
    0.80
    标记
    0.80
     marking
    0.80
    Marked
    0.79
    marked
    0.78
    Activations Density 0.533%

    No Known Activations