© 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. 214
    Prev
    Next
    INDEX
    Explanations

    questions and requests for help or suggestions related to problems or challenges

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

    Asks for thoughts, help, advice, or ideas

    np_acts-logits-general · gemini-2.0-flash

    any advice or help

    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
    GEBURTS
    -0.79
     Administrativna
    -0.75
     autorytatywna
    -0.70
     Numerade
    -0.67
    ropractic
    -0.65
    ethene
    -0.62
    
    -0.58
     Савезне
    -0.58
    complexContent
    -0.57
    addPreferredGap
    -0.56
    POSITIVE LOGITS
     anyone
    0.93
     Anyone
    0.86
    anyone
    0.84
    Anyone
    0.82
     Anybody
    0.80
     anybody
    0.80
    Anybody
    0.77
    Alguien
    0.75
     please
    0.70
     pls
    0.70
    Activations Density 0.411%

    No Known Activations