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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3895
    Prev
    Next
    INDEX
    Explanations

    references to societal norms and the concept of hypocrisy

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

    contrasts and comparisons marked by the word "but" and related adversative conjunctions.

    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
    oa̍t
    -0.68
     Normdatei
    -0.67
     EconPapers
    -0.65
     otomatig
    -0.63
    OCCURRED
    -0.63
    omenclature
    -0.62
    tagHelperRunner
    -0.62
    ɵɵelementStart
    -0.61
     &___
    -0.60
    writeFieldEnd
    -0.60
    POSITIVE LOGITS
     diesmal
    2.06
    这次
    1.79
    今回は
    1.77
    這次
    1.76
    这一次
    1.73
    今回も
    1.50
    今回
    1.37
    今回の
    1.25
    此次
    1.21
     this
    1.12
    Activations Density 0.386%

    No Known Activations