© 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. 4617
    Prev
    Next
    INDEX
    Explanations

    phrases involving obligations or responsibilities

    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
    Doing
    -0.69
     Doing
    -0.68
    Done
    -0.66
     DOING
    -0.63
     Done
    -0.61
    writeFieldEnd
    -0.57
     ſt
    -0.53
     DONE
    -0.53
    doing
    -0.52
    done
    -0.49
    POSITIVE LOGITS
     does
    0.75
     do
    0.65
    WithIOException
    0.54
    adaptiveStyles
    0.53
     AssemblyCompany
    0.52
     did
    0.52
     jadx
    0.49
    __":
    0.47
    __':
    0.47
    Portale
    0.47
    Activations Density 0.227%

    No Known Activations