© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 14492
    Prev
    Next
    INDEX
    Explanations

    terms related to academic positions and administrative roles in universities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Organiser
    -0.36
     teenagers
    -0.34
    BACKEND
    -0.34
     crack
    -0.34
     hayal
    -0.33
     INSPECTION
    -0.33
    úblico
    -0.32
     indirizzo
    -0.32
    eynman
    -0.32
    𝟹
    -0.31
    POSITIVE LOGITS
     faculty
    1.36
     Faculty
    1.23
    Faculty
    1.21
    faculty
    1.13
     campus
    0.96
     dean
    0.94
     FACULTY
    0.92
     Dean
    0.91
    Dean
    0.89
     Provost
    0.89
    Activations Density 0.368%

    No Known Activations