© 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 - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 9267
    Prev
    Next
    INDEX
    Explanations

    occurrences of periods or full stops in the text

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

    Includes followed by .h

    np_acts-logits-general · gemini-2.0-flash

    h files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.82
    بوابة
    -0.81
     صوتيه
    -0.80
    ScopeManager
    -0.80
     الرياضيه
    -0.77
    BeginContext
    -0.75
    
    -0.75
     <<<<<<<<<<<<<<
    -0.73
    脚注の使い方
    -0.71
    TemporalType
    -0.70
    POSITIVE LOGITS
    dart
    0.91
    dar
    0.58
     dart
    0.57
     Dart
    0.55
    Dart
    0.53
     Dar
    0.46
     darts
    0.40
     Starr
    0.39
     Lijst
    0.39
    Dar
    0.39
    Activations Density 0.082%

    No Known Activations