© 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. 1277
    Prev
    Next
    INDEX
    Explanations

    phrases indicating hypothetical or conditional situations

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

    counterfactual conditional statements expressing what would have happened under different circumstances.

    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
     increasingly
    -0.48
     faut
    -0.40
     sementara
    -0.40
    暂时
    -0.38
     zuneh
    -0.38
     erstmal
    -0.38
     essentiellement
    -0.37
    parece
    -0.36
     zatím
    -0.35
     kasarigan
    -0.34
    POSITIVE LOGITS
     hubiera
    1.13
     hätte
    1.08
     hubieran
    1.06
     hubiese
    1.04
     hätten
    0.98
     had
    0.86
     avrebbero
    0.85
     aurait
    0.83
     eût
    0.81
     avrebbe
    0.81
    Activations Density 0.460%

    No Known Activations