© 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. 9-GEMMASCOPE-RES-16K
    6. 10038
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to quantum mechanics and superconductivity

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

    text from scientific papers with academic citations and technical terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.66
     titolata
    -0.65
    zzleHttp
    -0.59
    ientôt
    -0.58
     queſta
    -0.58
     Autorizaciones
    -0.57
    amentlich
    -0.56
     pubblici
    -0.56
    épar
    -0.56
    appartamento
    -0.56
    POSITIVE LOGITS
     extreme
    0.35
     Suarez
    0.29
    SerializeField
    0.28
     challenge
    0.28
     Extreme
    0.27
    BERG
    0.27
    PhysRevLett
    0.26
    XmlIgnore
    0.26
    extreme
    0.26
     rather
    0.25
    Activations Density 4.896%

    No Known Activations