© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 3705
    Prev
    Next
    INDEX
    Explanations

    the repetition of the prefix "un" indicating negation or lack of something

    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
    ing
    -0.97
    ené
    -0.93
     lye
    -0.83
    ený
    -0.83
    ená
    -0.82
    Bae
    -0.81
    er
    -0.75
     Wale
    -0.75
    UDC
    -0.74
     debtors
    -0.74
    POSITIVE LOGITS
    oglobulin
    0.95
    Injectable
    0.89
     Aitken
    0.86
    Nonnull
    0.85
     Merritt
    0.84
    otherapy
    0.82
     Brack
    0.81
    diat
    0.81
     Cun
    0.79
     Quig
    0.79
    Activations Density 0.197%

    No Known Activations