© 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. 3888
    Prev
    Next
    INDEX
    Explanations

    information on job losses, particularly in factory settings or industry contexts

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

    words related to loss, decline, or reduction in quantity or value.

    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
    +#+
    -0.47
     surla
    -0.43
    Ārējās
    -0.41
    riwal
    -0.35
    UserScript
    -0.35
    дян
    -0.35
    랐
    -0.35
     Vle
    -0.34
     []).
    -0.34
     mouseY
    -0.33
    POSITIVE LOGITS
     loss
    3.08
     losses
    2.77
     Loss
    2.69
    Loss
    2.61
     lost
    2.55
    loss
    2.50
     loses
    2.41
     Losses
    2.38
     losing
    2.38
     LOSS
    2.36
    Activations Density 0.573%

    No Known Activations