© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 1277
    Prev
    Next
    INDEX
    Explanations

    discussions about the treatment of individuals, particularly in relation to equality and respect across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.41
    優れた
    -0.38
     [*]
    -0.36
     effective
    -0.36
     readily
    -0.35
     tarvit
    -0.35
     чудо
    -0.35
     expérimentés
    -0.35
    ⓧ
    -0.35
     valid
    -0.34
    POSITIVE LOGITS
     differently
    1.39
     correctly
    0.82
     accordingly
    0.82
     incorrectly
    0.80
    correctly
    0.74
     diffé
    0.73
    differ
    0.73
     similarly
    0.71
     Differ
    0.71
     autrement
    0.66
    Activations Density 0.582%

    No Known Activations