© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15287
    Prev
    Next
    INDEX
    Explanations

    instances of the word "start" and variations related to beginning or initiating something

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

    The token "start" or "Start"

    np_acts-logits-general · gemini-2.0-flash

    start and beginning

    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
    '},
    
    -0.69
     esternos
    -0.66
     passada
    -0.65
    Alpes
    -0.64
    LEncoder
    -0.63
    autaire
    -0.62
    honneur
    -0.60
     Anglais
    -0.60
    로운
    -0.59
     społecz
    -0.58
    POSITIVE LOGITS
     afresh
    0.84
     START
    0.74
    START
    0.74
     Start
    0.73
    ต้น
    0.73
     anew
    0.70
     Starts
    0.68
     start
    0.67
    Starts
    0.66
     开始
    0.64
    Activations Density 0.075%

    No Known Activations