© 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. 0-GEMMASCOPE-RES-16K
    6. 10997
    Prev
    Next
    INDEX
    Explanations

    expressions and terms related to medical or biological processes, particularly those involving recruitment and response mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eventdata
    -0.42
    Pró
    -0.41
    vertx
    -0.41
     Yos
    -0.41
     keter
    -0.41
    énario
    -0.39
    DropTable
    -0.38
     enfer
    -0.36
    EClass
    -0.36
     Felicia
    -0.35
    POSITIVE LOGITS
     straight
    0.67
     Sort
    0.65
     stra
    0.64
     Straight
    0.63
    straight
    0.60
     STRA
    0.59
     sort
    0.57
    Stra
    0.57
     str
    0.57
     Clear
    0.56
    Activations Density 1.761%

    No Known Activations