© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 58055
    Prev
    Next
    INDEX
    Explanations

    phrases related to introspection and self-reflection in digital interactions

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

    responses to questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.90
    CloseOperation
    -0.82
    Personendaten
    -0.81
     '\\;'
    -0.76
    contentLoaded
    -0.75
    rungsseite
    -0.74
     ujednoznacz
    -0.72
    исленность
    -0.71
    enterOuterAlt
    -0.71
    KURZBESCHREIBUNG
    -0.70
    POSITIVE LOGITS
    </h2>
    0.40
    RED
    0.38
      
    0.37
    V
    0.37
    F
    0.37
    Real
    0.37
     mens
    0.34
     ram
    0.33
                                   
    0.33
    <em>
    0.33
    Activations Density 0.122%

    No Known Activations