© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8304
    Prev
    Next
    INDEX
    Explanations

    significant numerical data and terms related to business and finance

    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
     Wiktionnaire
    -0.47
    oa̍t
    -0.45
     deleg
    -0.40
     recursively
    -0.37
     preven
    -0.37
    Rifer
    -0.35
     limiti
    -0.35
    ścioła
    -0.35
    engaruhi
    -0.35
     fascic
    -0.35
    POSITIVE LOGITS
     promises
    0.84
     marks
    0.78
     marked
    0.77
     markiert
    0.73
     tarjo
    0.72
    marked
    0.71
     promised
    0.68
     affords
    0.68
     promise
    0.67
     menghadirkan
    0.66
    Activations Density 0.399%

    No Known Activations