© 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. 31-GEMMASCOPE-RES-16K
    11. 3473
    Prev
    Next
    INDEX
    Explanations

    references to temporal events and significant dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    temporal expressions indicating specific times, dates, and durations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eſ
    -0.54
     Houſe
    -0.53
     ſind
    -0.52
     Majefty
    -0.52
     eſſ
    -0.51
    sizeCache
    -0.50
    ſelves
    -0.49
    angliski
    -0.49
     tranſ
    -0.49
     leaſt
    -0.48
    POSITIVE LOGITS
     onwards
    0.49
    +:+
    0.46
     commencing
    0.43
     itself
    0.41
    éndole
    0.40
    WriteBarrier
    0.38
     postIndex
    0.36
    itself
    0.35
     Verlauf
    0.35
     Vikipedi
    0.35
    Activations Density 0.211%

    No Known Activations