© 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. 37-GEMMASCOPE-RES-16K
    11. 883
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to time references, specifically focusing on the word "last."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     later
    -0.35
    Història
    -0.31
     później
    -0.31
     beitragen
    -0.28
    ira
    -0.28
     nyingi
    -0.28
    house
    -0.28
    Explanation
    -0.28
     später
    -0.28
     künftig
    -0.27
    POSITIVE LOGITS
    resort
    0.84
     resort
    0.82
    Resort
    0.81
    minute
    0.80
     minute
    0.75
    ingly
    0.75
     Resort
    0.74
    straw
    0.73
     ditch
    0.71
    ditch
    0.71
    Activations Density 0.090%

    No Known Activations