© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15650
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and reflections on personal experiences

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

    expressions of perseverance and resilience in the face of adversity.

    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
     fubject
    -0.47
    onoi
    -0.45
     lazily
    -0.44
    遠慮
    -0.42
     obfer
    -0.40
     lazy
    -0.40
     eaves
    -0.39
    RTGC
    -0.38
    MigrationBuilder
    -0.37
    MockMvc
    -0.37
    POSITIVE LOGITS
     resilience
    1.02
     resilient
    0.97
     resiliency
    0.95
     Resili
    0.91
    Resili
    0.86
     Resilience
    0.86
     persevere
    0.86
     persever
    0.81
     resili
    0.79
     optimism
    0.79
    Activations Density 0.379%

    No Known Activations