© 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. 38-GEMMASCOPE-RES-16K
    11. 8716
    Prev
    Next
    INDEX
    Explanations

    preferences and subjective opinions regarding personal choices and experiences

    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
     становника
    -0.31
    VersionUID
    -0.29
    |};
    -0.29
    erçe
    -0.28
     Teufel
    -0.28
    šit
    -0.28
    //
    -0.28
    теризу
    -0.28
    novation
    -0.27
    圍
    -0.27
    POSITIVE LOGITS
     preference
    3.48
     prefer
    3.47
     preferred
    3.33
    prefer
    3.14
     Prefer
    3.14
     prefers
    3.13
     Preference
    3.06
     preferring
    2.98
    Prefer
    2.98
    preference
    2.95
    Activations Density 0.887%

    No Known Activations