© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28230
    Prev
    Next
    INDEX
    Explanations

    discussions about benefits and harms in medical or economic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    benefits versus harm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reportWebVitals
    -0.84
     فريبيس
    -0.67
     صوتيه
    -0.61
    kegaard
    -0.60
    ContextHolder
    -0.59
     Bourgoin
    -0.57
    numerusform
    -0.55
    acherous
    -0.55
    SOUNDBITE
    -0.53
     otomatig
    -0.53
    POSITIVE LOGITS
     realized
    0.58
     архивлан
    0.58
     potential
    0.52
     pelanggan
    0.52
     potentiel
    0.51
     klant
    0.50
     realised
    0.50
     realization
    0.50
     realisation
    0.50
    imide
    0.47
    Activations Density 0.151%

    No Known Activations