© 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. 12911
    Prev
    Next
    INDEX
    Explanations

    terms related to future economic scenarios and predictions

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

    future predictions and forecasts about societal trends and changes.

    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
     senere
    -0.35
     later
    -0.32
    žka
    -0.32
     pozdě
    -0.31
     tidigare
    -0.30
    ếng
    -0.30
     vidare
    -0.30
     senare
    -0.30
     guitarra
    -0.30
    最终
    -0.30
    POSITIVE LOGITS
    StoryboardSegue
    1.03
     generations
    0.87
    tableFuture
    0.82
    proofing
    0.74
    存于互联网档案馆
    0.73
     proofing
    0.72
    ViewFeatures
    0.71
     tense
    0.71
     prospects
    0.69
    Portale
    0.69
    Activations Density 0.147%

    No Known Activations