© 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. 14766
    Prev
    Next
    INDEX
    Explanations

    references to time durations or lengths of experience

    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
     momentarily
    -0.43
     momentary
    -0.42
    一天
    -0.41
    一日
    -0.35
    oweit
    -0.34
    三日
    -0.34
     weeks
    -0.34
     briefly
    -0.33
     چند
    -0.33
     shortly
    -0.33
    POSITIVE LOGITS
     existence
    0.84
     consecu
    0.82
    existence
    0.81
     CreateTagHelper
    0.78
     подряд
    0.76
     continuous
    0.70
     existencia
    0.69
    continuous
    0.69
     uninterrupted
    0.69
     hinweg
    0.68
    Activations Density 0.385%

    No Known Activations