© 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. 28-GEMMASCOPE-RES-16K
    6. 7492
    Prev
    Next
    INDEX
    Explanations

    technical terms and components related to machinery and electrical engineering

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

    preceding company suffixes

    np_acts-logits-general · gemini-2.0-flash

    driver circuit

    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
    Personendaten
    -0.52
    GEBURTSDATUM
    -0.50
    jsxFileName
    -0.48
    jsonwebtoken
    -0.47
    BeginContext
    -0.45
     externi
    -0.44
    __*/
    -0.42
    middels
    -0.41
    EDEFAULT
    -0.41
     MainAxisSize
    -0.40
    POSITIVE LOGITS
     RIPRODUZIONE
    0.55
    bonucleic
    0.47
     aéri
    0.45
     ainfi
    0.45
     cuchara
    0.45
     přep
    0.44
     capucha
    0.43
     feroit
    0.42
     delar
    0.41
     deberes
    0.41
    Activations Density 1.416%

    No Known Activations