© 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. 14769
    Prev
    Next
    INDEX
    Explanations

    references to economic conditions and their effects on individuals and groups

    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
    どうしても
    -0.67
    Personendaten
    -0.66
     Obviously
    -0.56
    Obviously
    -0.55
     obviously
    -0.54
    やはり
    -0.51
     évidemment
    -0.51
    eraard
    -0.51
    引き続き
    -0.51
    obviously
    -0.50
    POSITIVE LOGITS
     almost
    0.99
     literally
    0.94
     literalmente
    0.94
     practically
    0.93
     едва
    0.87
     actually
    0.85
    almost
    0.85
     downright
    0.84
    literally
    0.83
     addirittura
    0.82
    Activations Density 0.553%

    No Known Activations