© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12537
    Prev
    Next
    INDEX
    Explanations

    terms related to the stages or progression of diseases and medical conditions

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

    Stages of disease or processes

    np_acts-logits-general · gemini-2.0-flash

    stages, phases, and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lenker
    -0.59
    rawDesc
    -0.54
    SourceChecksum
    -0.53
     CreateTagHelper
    -0.51
     IBOutlet
    -0.51
    XmlAccessType
    -0.50
     ledig
    -0.50
     Pacer
    -0.49
    strix
    -0.49
     оригіналу
    -0.48
    POSITIVE LOGITS
     stage
    2.20
     stages
    2.16
     Stage
    1.88
    Stage
    1.82
    stage
    1.79
     Stages
    1.79
     STAGE
    1.75
    stages
    1.73
    Stages
    1.72
     phase
    1.63
    Activations Density 0.741%

    No Known Activations