© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 10669
    Prev
    Next
    INDEX
    Explanations

    negative qualifiers and limitations related to treatments or medical recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Either
    -0.65
    either
    -0.58
     Either
    -0.57
     either
    -0.57
     entweder
    -0.54
    slightly
    -0.53
     slightly
    -0.53
     légèrement
    -0.52
     tantôt
    -0.51
     leggermente
    -0.50
    POSITIVE LOGITS
     yet
    0.66
     harmed
    0.62
     necessarily
    0.59
     disturb
    0.59
     exceed
    0.57
     currently
    0.56
     permitted
    0.55
     interfere
    0.54
     anymore
    0.52
     bothered
    0.52
    Activations Density 0.798%

    No Known Activations