© 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. 21-GEMMASCOPE-RES-16K
    11. 15676
    Prev
    Next
    INDEX
    Explanations

    phrases indicating criticism or mockery towards individuals or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.72
    <bos>
    -0.70
     fevere
    -0.69
     raiſ
    -0.67
    DoubleQuotes
    -0.66
     ſta
    -0.64
     auffi
    -0.64
    𝟹
    -0.63
     poffible
    -0.62
     ſever
    -0.61
    POSITIVE LOGITS
     bullshit
    1.69
     crap
    1.59
     shit
    1.48
     nonsense
    1.34
     idiots
    1.31
    shit
    1.29
     idiot
    1.28
     fuck
    1.27
     assholes
    1.27
     shite
    1.26
    Activations Density 0.385%

    No Known Activations