© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 228
    Prev
    Next
    INDEX
    Explanations

    subjective personal experiences and reflections

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

    first-person and second-person pronouns

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

    achieved became

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     raging
    -0.45
     presence
    -0.42
     munc
    -0.42
     perusal
    -0.41
     autonome
    -0.40
    ')")
    -0.40
     corrida
    -0.40
     destiny
    -0.39
     presença
    -0.39
     ausgeführt
    -0.39
    POSITIVE LOGITS
     achieve
    0.78
     achieved
    0.77
    fjspx
    0.76
    Achie
    0.74
     achieves
    0.74
     ensure
    0.68
     became
    0.68
     Obtaining
    0.67
     Achieve
    0.67
     Became
    0.66
    Activations Density 0.056%

    No Known Activations