© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 92
    Prev
    Next
    INDEX
    Explanations

    descriptions of character traits and emotions related to individual interactions

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

    Follows a quotation mark or dialogue introduction

    np_acts-logits-general · gemini-2.0-flash

    declaration of personal opinion

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     dude
    -1.07
     dudes
    -0.96
     guy
    -0.94
     guys
    -0.94
     lenker
    -0.90
     freakin
    -0.90
     homie
    -0.88
     shit
    -0.87
     Dude
    -0.86
     fuckin
    -0.85
    POSITIVE LOGITS
     lovely
    0.81
     delightful
    0.80
     wonderful
    0.76
    lovely
    0.70
    wonderful
    0.69
     dreadful
    0.66
     charming
    0.66
     marvellous
    0.66
     splendid
    0.65
    Lovely
    0.64
    Activations Density 0.418%

    No Known Activations