© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 4660
    Prev
    Next
    INDEX
    Explanations

    imperatives or commands related to initiating actions

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

    Sentences beginning with "Start" or "Starts"

    np_acts-logits-general · gemini-2.0-flash

    startstarting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Viki
    -0.82
    glBindBuffer
    -0.79
    }\]
    -0.78
    
    -0.75
     MyBatis
    -0.75
    InjectAttribute
    -0.74
    requireNonNull
    -0.73
    ellees
    -0.72
     Coliseum
    -0.72
    enumi
    -0.72
    POSITIVE LOGITS
    START
    1.04
     Start
    1.00
     START
    1.00
     Starts
    0.99
    Start
    0.93
    starts
    0.92
     starts
    0.92
    getStart
    0.90
    Starts
    0.90
     start
    0.87
    Activations Density 0.143%

    No Known Activations