© 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. 3-GEMMASCOPE-RES-16K
    11. 7904
    Prev
    Next
    INDEX
    Explanations

    derogatory or offensive language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.58
     modernize
    -0.55
    VIAF
    -0.55
     ویکی‌پدیای
    -0.54
     Ders
    -0.53
    原始内容存档于
    -0.52
    PROBE
    -0.51
    RTGC
    -0.51
    بوابة
    -0.51
    Tall
    -0.49
    POSITIVE LOGITS
     shit
    1.97
     crap
    1.72
     SHIT
    1.71
     Shit
    1.68
    shit
    1.66
    Shit
    1.61
     shite
    1.45
     shits
    1.45
    crap
    1.31
    Crap
    1.25
    Activations Density 0.381%

    No Known Activations