© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 205
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the start or initiation of an action

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

    "begin" or "began"

    np_acts-logits-general · gemini-2.0-flash

    beginning or starting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acamata
    -0.50
     Spreadsheet
    -0.45
     Verkehrs
    -0.45
    nosaurus
    -0.44
    şört
    -0.44
    ỡng
    -0.42
     vassal
    -0.41
     TRAFFIC
    -0.41
    arache
    -0.40
    ضايا
    -0.40
    POSITIVE LOGITS
     Begin
    0.98
     begins
    0.95
     Begins
    0.94
    Begin
    0.94
     begin
    0.93
    begins
    0.92
     begun
    0.90
     beginning
    0.87
    beginning
    0.87
     Beginning
    0.84
    Activations Density 0.105%

    No Known Activations