© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 13034
    Prev
    Next
    INDEX
    Explanations

    terms related to patient demographics and clinical study details in the context of various cancers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.60
    getItemId
    -0.54
     esternos
    -0.52
    ruptedException
    -0.50
    stdc
    -0.49
    XmlAccessType
    -0.49
    rientes
    -0.49
     HasFactory
    -0.49
    LEncoder
    -0.48
    cutting
    -0.48
    POSITIVE LOGITS
     treated
    0.78
     receiving
    0.69
     presenting
    0.69
     undergoing
    0.66
     who
    0.64
     typelib
    0.62
     tratados
    0.59
     aged
    0.59
    ConstraintMaker
    0.58
     randomized
    0.57
    Activations Density 1.075%

    No Known Activations