© 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. 21-GEMMASCOPE-RES-16K
    11. 12332
    Prev
    Next
    INDEX
    Explanations

    emotional and relational dynamics, particularly around loss and caring actions

    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
     praticamente
    -0.70
    Darn
    -0.70
     Aufgrund
    -0.68
     sumamente
    -0.68
    viamente
    -0.67
     äußerst
    -0.65
     extremadamente
    -0.64
     Asimismo
    -0.63
    )!
    -0.63
     např
    -0.63
    POSITIVE LOGITS
     fucking
    0.71
    fucking
    0.66
    noons
    0.66
    genstein
    0.65
     fucked
    0.64
    fuck
    0.62
     stillness
    0.58
     fuck
    0.58
     nameless
    0.56
    رشف
    0.55
    Activations Density 0.660%

    No Known Activations