Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 8493
    Prev
    Next
    INDEX
    Explanations

    specific types of biochemical markers related to diabetes and insulin production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.69
     ब्रेकडाउन
    -0.68
     kasarigan
    -0.68
    Referències
    -0.65
     فريبيس
    -0.63
     AssemblyCompany
    -0.63
     Normdatei
    -0.62
     CreateTagHelper
    -0.61
     AssemblyTitle
    -0.60
    Erreferentziak
    -0.60
    POSITIVE LOGITS
     '',
    
    0.44
    &-
    0.42
     "");
    
    0.41
    ‐
    0.41
    store
    0.41
    ajar
    0.40
     
    0.40
    ​​
    0.39
    space
    0.39
    ­
    0.39
    Activations Density 0.896%

    No Known Activations