© 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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7212
    Prev
    Next
    INDEX
    Explanations

    medical terms and classifications related to disorders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     mergeFrom
    -0.59
    SourceChecksum
    -0.57
    IBOutlet
    -0.55
    IsContent
    -0.51
    afio
    -0.50
    Referenties
    -0.50
    ISupport
    -0.50
    WaitGroup
    -0.50
    appro
    -0.45
    GraphicsUnit
    -0.42
    POSITIVE LOGITS
    </thead>
    0.69
     coding
    0.63
     codes
    0.62
    subsubsection
    0.60
     Coding
    0.60
     код
    0.59
    Empereur
    0.59
     Holocene
    0.59
    Codes
    0.58
     getCode
    0.58
    Activations Density 0.467%

    No Known Activations