© 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. 9128
    Prev
    Next
    INDEX
    Explanations

    elements of conflict, chaos, and emotional responses in dramatic scenarios

    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
     Normdatei
    -0.75
    asmuch
    -0.69
     insofar
    -0.68
     inasmuch
    -0.68
    ślę
    -0.64
    之所以
    -0.64
     puisqu
    -0.64
     grundsätzlich
    -0.63
     gerne
    -0.63
     antaranya
    -0.63
    POSITIVE LOGITS
     hundreds
    1.05
     thousands
    1.01
    thousands
    0.98
     dozens
    0.97
    hundreds
    0.93
     Hundreds
    0.92
    Hundreds
    0.91
     Thousands
    0.90
     everywhere
    0.87
    Thousands
    0.87
    Activations Density 0.209%

    No Known Activations