© 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. 28-GEMMASCOPE-RES-16K
    11. 8186
    Prev
    Next
    INDEX
    Explanations

    instances of private or intimate conversations and actions

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

    privacy, seclusion, and isolation

    np_acts-logits-general · gemini-2.0-flash

    private and secluded spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTEE
    -0.48
    AddTagHelper
    -0.44
    MessageOf
    -0.37
    inSlope
    -0.37
    migrationBuilder
    -0.35
     kors
    -0.34
     resident
    -0.33
     تعدى
    -0.33
    <!--[
    -0.32
    autorest
    -0.32
    POSITIVE LOGITS
     secluded
    1.05
     isolated
    0.95
     privately
    0.86
     Isolated
    0.85
     private
    0.82
    isolated
    0.81
     privacy
    0.80
    Isolated
    0.76
     hidden
    0.73
     seclusion
    0.73
    Activations Density 0.319%

    No Known Activations