© 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. 28-GEMMASCOPE-RES-16K
    11. 9650
    Prev
    Next
    INDEX
    Explanations

    instructions related to parents or guardians of students

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

    before "portal" or related terms

    np_acts-logits-general · gemini-2.0-flash

    online portals and platforms

    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
     redacción
    -0.33
     leggen
    -0.33
     especiales
    -0.31
    sscanf
    -0.30
     perfetta
    -0.28
     HasFactory
    -0.28
     muñecas
    -0.28
    งาม
    -0.28
     Brasileira
    -0.28
     Preguntas
    -0.28
    POSITIVE LOGITS
     portal
    1.13
     Portal
    1.05
     portals
    0.97
    portal
    0.94
     online
    0.93
    Portal
    0.89
     Online
    0.87
     platform
    0.84
     Portail
    0.80
    Online
    0.79
    Activations Density 0.349%

    No Known Activations