© 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. 4692
    Prev
    Next
    INDEX
    Explanations

    phrases related to destruction and its consequences

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

    words and phrases describing negative consequences or harm to individuals and their lives.

    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
     allá
    -0.30
    SerializeField
    -0.30
     each
    -0.27
     Each
    -0.26
    fillna
    -0.26
    Each
    -0.25
    changed
    -0.25
    ませんが
    -0.24
     enhanced
    -0.23
     compare
    -0.23
    POSITIVE LOGITS
    せっかく
    1.34
    好不容易
    1.15
    本来
    0.92
     ohnehin
    0.87
    parsedMessage
    0.87
    原本
    0.84
    valuable
    0.84
     precious
    0.84
    貴重な
    0.83
    大事な
    0.83
    Activations Density 0.854%

    No Known Activations