© 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. 2175
    Prev
    Next
    INDEX
    Explanations

    terms related to change, both in context and sentiment over time

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

    temporal or progressive language indicating change, growth, or development over time.

    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
    bootstrapcdn
    -0.80
    ]")]
    -0.76
    <unused42>
    -0.74
    <unused43>
    -0.74
    <unused74>
    -0.74
    <unused41>
    -0.74
    <unused8>
    -0.74
    <unused51>
    -0.73
    <unused14>
    -0.73
    [@BOS@]
    -0.73
    POSITIVE LOGITS
     as
    1.71
     καθώς
    0.97
     while
    0.90
     mentre
    0.89
    随着
    0.88
     enquanto
    0.87
     mientras
    0.85
     habang
    0.84
     terwijl
    0.81
    隨著
    0.78
    Activations Density 0.605%

    No Known Activations