© 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. 4049
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and social structures

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

    Followed by "nature" or "status"

    np_acts-logits-general · gemini-2.0-flash

    nature or status

    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
    ospels
    -0.27
    《
    -0.26
     aDecoder
    -0.25
     released
    -0.23
    ora
    -0.23
    Care
    -0.23
    IRE
    -0.23
     C
    -0.22
    Dis
    -0.21
    Pre
    -0.21
    POSITIVE LOGITS
    ness
    1.30
     nature
    1.18
    ishness
    1.02
    nature
    0.97
    iness
    0.95
     natureza
    0.94
    NESS
    0.93
    yness
    0.91
     بودن
    0.90
    veness
    0.89
    Activations Density 0.821%

    No Known Activations