© 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. 6695
    Prev
    Next
    INDEX
    Explanations

    references to self-awareness and emotional intelligence

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

    phrases containing "self-" followed by a reflective or emotional state word.

    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
    CppMethod
    -0.54
    ConstraintMaker
    -0.54
    enterOuterAlt
    -0.53
    AddTagHelper
    -0.51
    الحياه
    -0.49
     BoxDecoration
    -0.48
    WireFormatLite
    -0.47
     autorytatywna
    -0.47
     ſind
    -0.46
    المناصب
    -0.46
    POSITIVE LOGITS
     self
    2.64
     Self
    2.25
    Self
    2.17
     SELF
    2.11
    self
    2.11
    SELF
    1.89
     Selbst
    1.84
    自我
    1.71
    Selbst
    1.57
    自
    1.55
    Activations Density 0.451%

    No Known Activations