© 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. 5888
    Prev
    Next
    INDEX
    Explanations

    sentences that discuss personal experiences or reflections over time

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

    statements or clauses beginning with "while" that introduce contrasting or qualifying information.

    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
     either
    -0.62
     Either
    -0.55
    Either
    -0.53
    either
    -0.53
     instead
    -0.50
     malah
    -0.47
     justru
    -0.46
     simply
    -0.45
     entweder
    -0.44
    ITHER
    -0.44
    POSITIVE LOGITS
     nominally
    1.05
     technically
    1.05
     ostensibly
    0.97
     admittedly
    0.93
     parezca
    0.89
     theoretically
    0.88
    看似
    0.88
    一見
    0.87
     وتسجيلات
    0.85
     outwardly
    0.84
    Activations Density 0.639%

    No Known Activations