© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 87732
    Prev
    Next
    INDEX
    Explanations

    phrases related to attitudes and perceptions

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

    personal or societal attitudes

    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
    
    -0.46
    Parcelize
    -0.42
      
    -0.41
    anthene
    -0.41
    دانشنامهٔ
    -0.41
     Vikipedi
    -0.40
    IndentedString
    -0.40
     Corm
    -0.40
     fathoms
    -0.38
     Traces
    -0.38
    POSITIVE LOGITS
    Attitude
    1.13
     Attitude
    1.11
     attitude
    1.11
    attitude
    1.09
     attitudes
    1.05
     actitud
    1.02
     Attitudes
    1.02
     actitudes
    0.92
     atitude
    0.91
    titudes
    0.86
    Activations Density 0.006%

    No Known Activations