© 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. 5842
    Prev
    Next
    INDEX
    Explanations

    expressions of personal beliefs and values regarding responsibility and communication

    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
     Dont
    -0.89
     doesnt
    -0.88
     didnt
    -0.86
    Dont
    -0.84
     dont
    -0.84
     fuckin
    -0.84
     DONT
    -0.80
     couldnt
    -0.79
     isnt
    -0.79
     wouldnt
    -0.78
    POSITIVE LOGITS
     >>
    0.69
     --
    0.63
     ♪
    0.59
     kommenden
    0.46
     "--
    0.43
    ♪
    0.41
     vergangenen
    0.40
     ontem
    0.40
    ("--
    0.39
    quehanna
    0.38
    Activations Density 0.036%

    No Known Activations