© 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. 14833
    Prev
    Next
    INDEX
    Explanations

    references to specific scientific components and processes

    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
    TestingModule
    -0.51
    oa̍t
    -0.48
     Vikipedi
    -0.45
     więc
    -0.45
     Meaning
    -0.44
    Meaning
    -0.44
    Hentet
    -0.43
     precludes
    -0.43
     bởi
    -0.42
    ktm
    -0.41
    POSITIVE LOGITS
     releasing
    1.07
     gaining
    1.02
     depositing
    1.01
     bringing
    0.99
     seizing
    0.98
     turning
    0.98
     destroying
    0.97
     acquiring
    0.96
     sending
    0.95
     obtaining
    0.95
    Activations Density 0.954%

    No Known Activations