© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 37714
    Prev
    Next
    INDEX
    Explanations

    themes related to emotional safety and protection in various contexts

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

    protection and shielding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    queryInterface
    -0.49
    AndroidJUnit
    -0.45
    FirstResponder
    -0.44
    ngdoc
    -0.43
     مرئيه
    -0.42
    memberof
    -0.41
     ProtoMessage
    -0.41
    setupUi
    -0.40
    textTheme
    -0.40
     stället
    -0.40
    POSITIVE LOGITS
     sheltered
    1.64
     shielded
    1.53
     protected
    1.51
    protected
    1.29
     shielding
    1.27
     Protected
    1.27
     protegido
    1.21
    Protected
    1.18
     protection
    1.17
     insulated
    1.13
    Activations Density 0.189%

    No Known Activations