© 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. 1254
    Prev
    Next
    INDEX
    Explanations

    debug information and error messages related to software, particularly focusing on SSH configurations and key management

    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
    +#+#
    -0.79
     StringTokenizer
    -0.79
    Tikang
    -0.71
    出版年
    -0.71
     nakalista
    -0.71
    IntoConstraints
    -0.68
    .*")]
    -0.67
    adaptiveStyles
    -0.66
    ValueStyle
    -0.65
     चीज़ों
    -0.65
    POSITIVE LOGITS
     [
    0.43
     ...
    0.36
     cannot
    0.36
     unknown
    0.36
     root
    0.35
     satisf
    0.34
     Encounter
    0.34
     fri
    0.34
     lost
    0.33
     unable
    0.33
    Activations Density 2.882%

    No Known Activations