© 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. 38-GEMMASCOPE-RES-16K
    11. 8523
    Prev
    Next
    INDEX
    Explanations

    terms related to coherence and interconnectedness in complex systems

    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
     CommonModule
    -0.56
    SourceChecksum
    -0.53
     defaultstate
    -0.49
    PMailer
    -0.49
    bootstrapcdn
    -0.47
     الرياضيه
    -0.47
     BrowserModule
    -0.44
    typeDefinition
    -0.44
    MENAFN
    -0.44
     Signalez
    -0.43
    POSITIVE LOGITS
    ent
    0.72
    ently
    0.71
    ents
    0.68
    ant
    0.64
    jent
    0.60
    dent
    0.60
    antly
    0.58
    uent
    0.57
    ient
    0.56
    erent
    0.55
    Activations Density 0.589%

    No Known Activations