© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 6976
    Prev
    Next
    INDEX
    Explanations

    terms related to respect and integrity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.42
     mxArray
    -0.40
     manio
    -0.40
     localised
    -0.40
     maquin
    -0.38
    quía
    -0.38
     Fatty
    -0.36
    ayaquil
    -0.35
     aveug
    -0.35
     JADX
    -0.35
    POSITIVE LOGITS
     Respect
    1.41
    Respect
    1.39
     respect
    1.38
    respect
    1.34
     RESPECT
    1.30
     respectful
    1.19
     respetar
    1.15
     respects
    1.13
     respecting
    1.13
     respected
    1.10
    Activations Density 0.167%

    No Known Activations