© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 31-GEMMASCOPE-RES-16K
    11. 7190
    Prev
    Next
    INDEX
    Explanations

    references to political integrity and health-related concerns, particularly around public perception and behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to concern, worry, or negative emotional responses.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.49
    BagLayout
    -0.47
    BorderLayout
    -0.39
    Predecesor
    -0.39
    zös
    -0.37
     виправивши
    -0.36
     jih
    -0.36
     Reims
    -0.35
     nuo
    -0.35
    /**
    -0.35
    POSITIVE LOGITS
     among
    3.42
    among
    3.08
     amongst
    2.84
     AMONG
    2.83
     Among
    2.69
    Among
    2.66
     parmi
    2.47
     wśród
    2.44
     среди
    2.44
     Amongst
    2.34
    Activations Density 1.106%

    No Known Activations