© 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. 8508
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to community, health, and ethical considerations

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

    followed by specific suffixes

    np_acts-logits-general · gemini-2.0-flash

    news format, motor drive, database search

    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
     şeyler
    -0.42
     ruinas
    -0.34
    esterno
    -0.34
     demandent
    -0.30
     şeyi
    -0.30
     cosas
    -0.30
     étrangers
    -0.29
    1
    -0.29
     berlebihan
    -0.29
     islas
    -0.28
    POSITIVE LOGITS
    <unused68>
    1.02
    <unused14>
    1.01
    <unused43>
    1.01
    <unused3>
    1.01
    <unused28>
    1.01
    [@BOS@]
    1.01
    <unused79>
    1.01
    <unused41>
    1.00
    <unused17>
    1.00
    <unused8>
    1.00
    Activations Density 1.292%

    No Known Activations