© 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. 16-GEMMASCOPE-RES-16K
    6. 13582
    Prev
    Next
    INDEX
    Explanations

    terms related to fine particles, their properties, and methods of production or manipulation in various materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nights
    -0.43
    pulumi
    -0.41
    cagon
    -0.38
    "}")
    -0.38
     Nights
    -0.38
     Signalez
    -0.36
    Наводи
    -0.36
    __":
    -0.35
     slots
    -0.35
    arbox
    -0.35
    POSITIVE LOGITS
    twimg
    0.73
     particles
    0.69
     partículas
    0.68
     particle
    0.66
    particles
    0.65
     particulate
    0.63
    particle
    0.63
    Particle
    0.62
     Particle
    0.60
     Particles
    0.60
    Activations Density 0.754%

    No Known Activations